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

The annotations already declare readOnly/openWorld/idempotent hints, and the description adds substantial behavior beyond them: the exact success shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}), the five enumerated refusal reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), and the honesty guarantee that answers are extracted 'using ONLY what the tool result contains' with verbatim-quote evidence. These are behavioral traits the structured annotations cannot convey.

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

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

Though long, the description contains zero waste: each sentence carries distinct information — value proposition, mechanism, success return shape, refusal contract, usage triggers, and cost trade-off. It is logically front-loaded (purpose → mechanism → contract → guidance) and never repeats what the annotations or schema already state.

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

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

There is no output schema, so the description compensates by fully documenting both the success and refusal response shapes, including the complete enumeration of refusal reasons. Combined with the 100%-covered input schema and the safety annotations (readOnly, idempotent, non-destructive), nothing an agent needs in order to invoke this tool correctly is missing.

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

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

Schema description coverage is 100% — the question parameter and all five aliases are already documented in the input schema, including the note that aliases are accepted. The description adds only indirect context (that the question triggers tool routing and argument filling), which explains mechanism rather than parameter format. With the schema carrying the full documentation burden, the baseline 3 applies.

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

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

The description opens with a specific, differentiated value proposition — 'Hallucination-resistant answer mode for high-stakes reads' — and contrasts itself against the sibling ask_pipeworx ('Same routing as ask_pipeworx... then EXTRACTS the answer using ONLY what the tool result contains'). It names the resource (5,908 tools across 1,540 sources) and the distinguishing mechanism (extractive grounding with explicit refusal), so an agent can tell it apart from ask_pipeworx and ask_pipeworx_beta without opening any schema.

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

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

Explicit when-to-use is given: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts', with concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also provides an explicit when-not-to-use with the named alternative and rationale: 'prefer ask_pipeworx for casual lookups' because this mode 'costs one extra LLM call'. This is complete, unambiguous routing guidance.

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