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

Annotations already convey read-only and idempotent; the description adds meaningful behavioral detail beyond them: it extracts only from tool results, returns verbatim evidence, refuses rather than invents, and enumerates all refusal reasons. It also discloses the extra LLM-call cost, which is not in the annotations.

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: mode definition, routing behavior, return shape, refusal contract, use cases, and cost tradeoff. It is front-loaded with the core purpose before the finer details.

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?

With no output schema, the description fully carries the return-value burden and does so completely: it specifies the success payload, the evidence field, confidence, source, and all refusal reasons. It also covers the invocation question, routing scope, cost, and when to prefer a sibling, making the tool self-sufficient for correct use.

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 the baseline of 3 applies. The description does not add parameter-level meaning beyond 'your question in natural language', but the schema already documents the required question and all aliases clearly, so no compensation is needed.

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 names the exact resource and mode: 'Hallucination-resistant answer mode' for 'high-stakes reads', and contrasts it directly with ask_pipeworx and ask_pipeworx_beta in the sibling list. It states what the tool does with a specific verb-like flow: route, fetch, extract, and either answer or refuse.

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?

It explicitly says when to use this mode ('when an answer will be quoted, cited, or acted on') and when not to ('prefer ask_pipeworx for casual lookups'), even naming the cost tradeoff. This is clear routing guidance that leaves nothing to inference.

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