Skip to main content
Glama

Leie

by io.github.pipeworx-io
OverviewDiscussionsAdmin

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 7,134 across 1854 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.

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. Changed5 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "question": "What was Apple's fiscal 2023 revenue?"
+  }
+]
    • addedInput schema / properties / ask
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / message
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • 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"
+}
    • 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."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnly/idempotent/openWorld); the description adds the real behavioral burden: a verbatim-evidence extraction contract, an enumerated refusal taxonomy with the exact refusal_reason values, and a disambiguated refusal_cause for llm_error ('wall' vs model-call failure). Cost and routing behavior are also disclosed. This is materially more than the annotations provide.

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 differentiator and the success/refusal contract before the usage guidance. Dense but the refusal_cause parenthetical ('wall_after_failure' etc.) is heavy detail that arguably belongs in the schema; otherwise nearly every sentence earns its place.

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?

No output schema exists, so the description carries the return shape itself — and it does, enumerating both success and refusal payloads including every field. Combined with the usage conditions and cost note, an agent has everything needed to call and interpret this correctly.

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 coverage is 100% and the aliases plus prefer_tool are fully documented in the schema itself, so baseline 3 applies. The description contributes context about routing and argument auto-filling but never mentions prefer_tool or the alias set, so it adds little beyond the structured fields.

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 ('hallucination-resistant answer mode') with a specific mechanism: routes across 7,134 tools, then EXTRACTS the answer using only the tool result. It is immediately distinguishable from ask_pipeworx, which is named as the non-grounded sibling.

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?

Explicit when-to-use ('whenever an answer will be quoted, cited, or acted on... financial verdicts, legal claims, medical lookups, public statements') and explicit when-not ('prefer ask_pipeworx for casual lookups'), with the cost tradeoff (one extra LLM call) given as the deciding criterion.

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

All Leie toolsInspect
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