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

Annotations only declare the safety profile (readOnly, idempotent, non-destructive, open world); the description adds substantial behavior beyond that, including the exact success payload, the enumerated refusal taxonomy, and the nested refusal_cause semantics for llm_error (wall vs route/threw/unparseable/wall_after_failure). It also discloses the cost differential against the sibling, which is the key operational tradeoff.

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?

Front-loads the core distinction ('hallucination-resistant answer mode for high-stakes reads') and then the decision rule, with no filler sentences. It is dense with nested parentheticals and a long refusal enumeration, which costs some readability, but nearly every clause carries information an agent needs.

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 carries the full burden of describing returns and does so precisely: success shape (answer, evidence, confidence, source, fetched_at, refusal_reason null) and failure shape with all refusal_reason values. Combined with the usage rule and cost note, nothing an agent needs to decide or call 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%, so the aliases and prefer_tool are already documented by the schema, and the baseline of 3 applies. The description does contextualize routing ('picks the right tool from 7,204'), which makes prefer_tool's purpose understandable, but it adds no new syntax, format, or constraint detail beyond the structured fields.

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 mode (hallucination-resistant grounded answering) and the exact mechanism: route to one of 7,204 tools, fill arguments, fetch, then extract the answer using ONLY the tool result. It explicitly contrasts with the sibling ask_pipeworx, so an agent can distinguish the two without opening either 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?

Gives a clear trigger condition (use whenever an answer will be quoted, cited, or acted on and facts must not be invented) with concrete examples (financial verdicts, legal claims, medical lookups, public statements), plus the inverse routing rule: prefer ask_pipeworx for casual lookups because this costs one extra LLM call.

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