Tools

Everything Stats Explorer exposes to your AI client: tools, resources and prompts.

10 capabilities10 tool

Automated heuristic

Tool docs quality: D — 10 tools graded

Average 52/100 for how clearly each description tells an AI client what the tool does, what it needs, and what it changes. It is not a security audit.

Grade A: 0
Grade B: 1
Grade C: 3
Grade D: 6
Grade F: 0

How grades work

ab_test_plantool
Visitors and days needed for an A/B test, or the smallest lift a given sample can detect
Description quality grade B, 75/100 · 2 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: passed20/20
  Length is in a useful range.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: passed20/20
  The description mentions what the tool takes.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
build_reporttool
only when you ask for one, and containing only the sections you tick. A completed hypothesis test becomes a write-up in the app's format: the question, the hypotheses, how it was tested (with steps 2–4), what was found, the verdict and base
Description quality grade C, 65/100 · 2 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: passed20/20
  Length is in a useful range.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: passed10/10
  Includes when or how to use it.
choose_testtool
Recommend the right test for a question
Description quality grade D, 45/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: not passed10/20
  A bit terse. One more clause about inputs or results would help.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
confidence_intervaltool
CI for a mean (t) or a proportion (Wilson)
Description quality grade D, 45/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: not passed10/20
  A bit terse. One more clause about inputs or results would help.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
create_visualizationtool
histogram, box plot, scatter (with least-squares line), bar (mean or count by category), line, and pie. These are the app's chart types. Returns an accessible SVG (light and dark mode) and can save it as .svg.
Description quality grade D, 40/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: passed20/20
  Length is in a useful range.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: not passed0/15
  This looks like a write action. Say what changes, and whether it can be undone.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
find_relationshipstool
Which columns relate most to a numeric outcome ("what drives X")
Description quality grade C, 55/100 · 3 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: passed20/20
  Length is in a useful range.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
group_summarytool
Totals, averages, medians, counts per category; top N (analytics)
Description quality grade D, 45/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: not passed10/20
  A bit terse. One more clause about inputs or results would help.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
inspect_data_filetool
Columns, types, missing values, categories and a preview of a data file
Description quality grade C, 55/100 · 3 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: passed20/20
  Length is in a useful range.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
start_analysistool
Classify the request (hypothesis test or exploration)
Description quality grade D, 45/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: not passed10/20
  A bit terse. One more clause about inputs or results would help.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.
workflow_statustool
Where the current analysis is, and the saved results
Description quality grade D, 45/100 · 4 to fix
- Has a description: passed20/20
  The tool has a description an AI client can read.
- Sensible length: not passed10/20
  A bit terse. One more clause about inputs or results would help.
- Starts with what it does: not passed0/15
  Open with an action verb, for example “Search issues…” or “Creates a label…”.
- Mentions its inputs: not passed0/20
  Say what the tool needs, for example “by issue number” or “takes a file path”.
- Explains side effects: passed15/15
  Looks read-only, so no disclosure is required. Saying “read-only” still helps.
- Gives usage guidance: not passed0/10
  Add when to use it, what it requires, or what to use instead.