QuestionPunk

Skill Run

skill_run

Have QuestionPunk's AI run an analysis skill on a survey's responses, in the app's analysis chat, and return the answer; every number and quote in it is checked against the responses by QuestionPunk. Spends the user's AI credits like a chat message (a turn that cites no evidence is not charged). Use it only when the user asks for QuestionPunk to run it or for its checked analysis, and say it uses their credits; otherwise run the skill yourself with skill_prompt. Takes up to two minutes; if it returns status 'running', call skill_run_get with the same surveyId and threadId. segment-comparison needs segmentQuestionId from skill_list's segmentQuestions. Pass a threadId from an earlier run to continue that conversation; otherwise a new chat thread is created in the app.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "surveyId": "<surveyId>",
      "skillId": "<skillId>"
    },
    "name": "skill_run"
  }
}

Input Schema

Name	Required	Description
`skillId`	Yes	A built-in id (executive-summary, segment-comparison, key-themes, recommendations) or a saved skill's id, from skill_list
`surveyId`	Yes	Survey ID (from survey_list)
`threadId`	No	Continue this analysis chat thread (from an earlier skill_run) instead of starting a new one
`segmentQuestionId`	No	For segment-comparison only: the question whose answers split respondents into groups (from skill_list with surveyId)

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations with non-obvious behavior: it consumes the user's AI credits, unevidenced turns are not charged, execution can take up to two minutes, and a 'running' status requires polling skill_run_get with the same surveyId and threadId. It also explains the side effect of thread creation, which the readOnlyHint=false annotation hints at but does not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose then progressively narrows to cost, invocation gating, timeout/polling, and parameter caveats. Dense but every clause carries actionable information; only the parenthetical credit-charging rule feels slightly detachable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers what an agent needs for a costly asynchronous operation: cost model, approval condition, timeout, and the exact follow-up call with required arguments. With an output schema present, return-value detail is correctly omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all four parameters; the description adds the conditional rule that segment-comparison requires segmentQuestionId sourced from skill_list's segmentQuestions, and clarifies that omitting threadId creates a new chat thread. That thread-creation detail is genuinely new relative to the schema, though most of the rest restates schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Uses a specific verb and resource: 'Have QuestionPunk's AI run an analysis skill on a survey's responses, in the app's analysis chat, and return the answer.' It also states the differentiator (every number and quote checked against responses), which separates it from a plain prompt-running sibling like skill_prompt.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive condition ('only when the user asks for QuestionPunk to run it or for its checked analysis'), an explicit alternative ('otherwise run the skill yourself with skill_prompt'), and a required user-facing disclosure about credits. No inference needed to choose between this and skill_prompt.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All QuestionPunk tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?