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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. On top of that, the description adds rich behavioral detail: the grounding constraint (answer extracted only from tool result), the full refusal mechanism with five explicit refusal_reason values, the exact success return shape, and the cost of one extra LLM call. The refusal semantics in particular are behavior an agent could never infer from annotations alone. No contradiction with 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: purpose, mechanism, return format, refusal reasons, usage context, and cost tradeoff. The core differentiator is front-loaded. It is longer than ideal, and the exact refusal enum list could be seen as verbose, but since there is no output schema, documenting the refusal contract in-band is justified.

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 tool with no output schema, the description fully covers the return contract, refusal behavior, success/error paths, and routing context. It also carries the alternative-selection guidance. Minor gaps: it doesn't specify how 'confidence' is derived or any evidence length cap, but these are secondary against the decision-relevant information that is present. This is complete enough for safe 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%, so the schema fully documents the single meaningful parameter (question) and its five aliases. The description adds behavioral context about how the question is processed (routed, arguments filled, data fetched, answer extracted) but no syntactic or format details beyond the schema. Per the baseline rule for high coverage, a 3 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?

The description opens with a specific, vivid purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It names the resource (Pipeworx data routed across 5,724 tools / 1497 sources) and the distinguishing behavior (extracts answers ONLY from tool results, or refuses). It explicitly contrasts with the sibling ask_pipeworx, so an agent can discriminate without opening schemas.

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 guidance: 'Use whenever an answer will be quoted, cited, or acted on... financial verdicts, legal claims, medical lookups, public statements.' It also gives a when-not-to-use with a named alternative and a concrete cost reason: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This is the gold standard for routing.

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