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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantial behavioral context beyond them: the extraction constraint ('EXTRACTS the answer using ONLY what the tool result contains'), the exact success return shape with evidence as a verbatim quote, and the full refusal contract enumerating five refusal_reason values (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). Since there is no output schema, this disclosure is essential and comprehensive. No contradiction with annotations exists.

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?

The description is dense but every sentence earns its place: core value proposition, routing mechanism, success/refusal return contract, use-case guidance, and cost tradeoff. The key differentiator ('Hallucination-resistant') is front-loaded, and the refusal-reason enumeration is compact despite covering five distinct failure modes. No filler or redundancy.

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?

For a single-free-text-parameter tool with no output schema, the description covers everything an agent needs: what the tool does, what it returns on success, what it returns on each failure class, when to prefer it, and its cost relative to the alternative. The annotations cover the safety profile, and the schema covers parameters, so no critical gap remains.

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% — all six parameters (question and its five aliases) are documented in the schema, so the baseline of 3 applies. The description does not add parameter-level detail, but it does enrich the parameter's purpose by explaining what the tool does with the question (routing, filling arguments, fetching, extracting). This is adequate but not more than the baseline warrants.

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 mode and purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly distinguishes itself from siblings (ask_pipeworx, ask_pipeworx_beta) by its grounded-extraction mechanism and explicit refusal behavior, and names its sibling relation directly ('Same routing as ask_pipeworx'). An agent can tell exactly what this tool does and how it differs from its nearest alternatives.

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?

The description gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete high-stakes examples. It also states when NOT to use it and names the alternative: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This is exemplary routing guidance with no inference required.

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