Skip to main content
Glama

Ask Pipeworx — Grounded

ask_pipeworx_grounded
Read-onlyIdempotent

Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx, picks the right tool from 7,553 across 2011 sources, fills arguments, fetches the data, then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. An "llm_error" also carries refusal_cause ("wall" = our time budget ended before any model call was made; "route"|"threw"|"unparseable"|"wall_after_failure" = a model call failed); refusal_reason itself is unchanged. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx, prefer ask_pipeworx for casual lookups.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "What was Apple's fiscal 2023 revenue?"
    },
    "name": "ask_pipeworx_grounded"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoAlias for question.
askNoAlias for question.
textNoAlias for question.
inputNoAlias for question.
queryNoAlias for question.
promptNoAlias for question.
messageNoAlias for question.
questionYesYour question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases.
prefer_toolNoRun this exact tool instead of letting the router choose, use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / prefer_tool / description
      Previous value: -"Run this exact tool instead of letting the router choose — use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed."New value: +"Run this exact tool instead of letting the router choose, use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed."
  2. Changed1 schema field changed
    • addedInput schema / properties / prefer_tool
      Added value: +{
      +  "description": "Run this exact tool instead of letting the router choose — use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed.",
      +  "type": "string"
      +}
  3. Changed3 schema fields changed
    • addedInput schema / properties / ask
      Added value: +{
      +  "description": "Alias for question.",
      +  "type": "string"
      +}
    • addedInput schema / properties / message
      Added value: +{
      +  "description": "Alias for question.",
      +  "type": "string"
      +}
    • changedInput schema / properties / question / description
      Previous value: -"Your question in natural language. Accepts query, q, prompt, text, input as aliases."New value: +"Your question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases."
  4. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "question": "What was Apple's fiscal 2023 revenue?"
      +  }
      +]
  5. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Adds real behavioral context beyond the annotations: an extra LLM call cost, an all-or-nothing refusal contract with enumerated refusal_reason values, and the refusal_cause encoding for llm_error. With readOnlyHint and idempotentHint already declaring the safety profile and no output schema present, the description is doing useful work, but the dense parenthetical enumeration of failure modes reads more like spec dump than guidance, and latency/rate expectations are unstated.

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 the core value proposition and the when-to-use rule before the return contract. Mostly tight, but the refusal_cause parenthetical is a heavy nested clause that could be flattened, and the benefit/cost framing is repeated across the first and last sentences.

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

Completeness4/5

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

No output schema exists, and the description compensates by spelling out the success payload shape (answer, evidence, confidence, source, fetched_at, refusal_reason) and every failure mode, which is what an agent needs to branch on. What is missing is how a refusal should be handled downstream and whether retries with prefer_tool are advisable.

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

Parameters3/5

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

Schema description coverage is 100%, with seven documented aliases for question and prefer_tool fully described, so the baseline is 3. The description adds routing context (arguments are auto-filled from the question, an exact tool can be forced) but adds no meaning beyond the schema for any individual parameter.

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?

States a specific mode (grounded, hallucination-resistant answering) plus the concrete pipeline: route among 7,553 tools, fill arguments, fetch, then extract only from the tool result. It is clearly differentiated from the sibling ask_pipeworx, so an agent can pick between them without opening either schema.

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 explicit when-to-use criteria ("whenever an answer will be quoted, cited, or acted on", with example domains like financial verdicts and legal claims) and names the alternative with the selecting condition ("prefer ask_pipeworx for casual lookups" because of the extra LLM call). Nothing is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.