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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety profile is covered. The description nonetheless adds substantial beyond-annotation behavior: the exact success payload shape, five enumerated refusal_reason values, the verbatim-extraction constraint, and the known cost of one extra LLM call. That is real added context, though it stops short of stating latency, truncation limits, or pagination behavior.

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?

Dense but front-loaded: purpose, then mechanism, then return/refusal contract, then usage rule, then cost trade-off. Every sentence carries distinct information and the alternative and its condition are stated last where they are easy to act on; no filler.

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 carries the return contract itself and does so completely, enumerating both the success fields (answer, evidence, confidence, source, fetched_at) and every refusal reason. For a tool that fans out to 6,717 tools and calls an LLM, the failure-mode disclosure is exactly what an agent needs.

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%, so all eight parameters (question plus seven documented aliases) are already explained by the schema itself. The description adds no syntax, format, or alias guidance beyond what the properties block provides, so the baseline 3 for a fully-documented schema is appropriate.

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?

States a specific verb (extract/answer), resource (grounded answer), and its differentiator from siblings: identical routing to ask_pipeworx but extraction constrained to the tool result. The opening phrase 'Hallucination-resistant answer mode for high-stakes reads' immediately distinguishes it from ask_pipeworx, ask_pipeworx_beta, and deep_research.

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?

Gives an explicit when-to-use rule ('whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts'), concrete trigger domains (financial verdicts, legal claims, medical lookups, public statements), and an explicit when-not/alternative ('prefer ask_pipeworx for casual lookups' with the cost reason). 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.