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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint, and the description adds substantial behavior beyond that: the refusal mechanism with its exact refusal_reason enum ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error'), the full success response shape with verbatim evidence, and the extra LLM call cost. This is rich, non-redundant disclosure, and it does not contradict the read-only 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?

Front-loaded with the core purpose in the first phrase, then proceeds in a logical order — mechanism, success return shape, refusal contract, usage guidance, cost tradeoff. Every sentence earns its place; there is zero redundancy despite covering a large amount of behavioral ground.

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?

Despite having no output schema, the description fully documents both the success and refusal response structures, which is the main missing-piece risk for a tool like this. Annotations cover the safety profile, the schema covers the one parameter, and the description covers routing scope, cost, and refusal semantics — nothing critical is missing for correct invocation.

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 coverage is 100% and the schema fully documents the question parameter with six aliases, so the baseline is 3. The description adds complementary processing semantics: the question is routed across '5,798 across 1517 sources' and 'fills arguments,' telling the agent the single required parameter is a high-level natural-language request that will be decomposed automatically — meaning beyond the schema's alias list.

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 purpose: 'Hallucination-resistant answer mode for high-stakes reads' and explains the mechanism ('EXTRACTS the answer using ONLY what the tool result contains'). It explicitly distinguishes itself from the sibling ask_pipeworx via 'Same routing as ask_pipeworx' plus the grounded-extraction difference, so an agent can tell them apart immediately.

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 explicit when-to-use: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements).' It also names the alternative and the deciding tradeoff: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' 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.