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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial behavioral context: the full success return shape {answer, evidence, confidence, source, fetched_at}, the explicit refusal envelope with all five refusal_reason enum values, the processing pipeline (routes → fills arguments → fetches → extracts), and the cost implication of one extra LLM call. 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?

Every sentence earns its place: the headline trait comes first, followed by mechanism, return shapes, usage guidance, and cost trade-off. It is longer than average, but the density of unique behavioral information justifies the length; nothing is redundant with the schema or annotations.

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 present, the description carries the full burden of explaining return values — and it does so comprehensively for both success and refusal paths, enumerating every refusal_reason. Combined with annotations covering safety and the schema covering the parameter, nothing an agent needs to select and invoke this tool 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% — the schema already documents the single 'question' parameter and its five aliases (query, q, prompt, text, input). The description adds context about what the question feeds into (routing and extraction) but no format or syntax detail beyond the schema, so the baseline 3 applies.

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-resource pair ('grounded answer mode' that 'EXTRACTS the answer using ONLY what the tool result contains') and distinguishes itself from the sibling ask_pipeworx by name ('Same routing as ask_pipeworx', 'Costs one extra LLM call vs ask_pipeworx'). The hallucination-resistant angle makes its identity unmistakable.

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?

Explicitly names when to use it ('whenever an answer will be quoted, cited, or acted on'), gives concrete domains (financial verdicts, legal claims, medical lookups, public statements), and states the exclusion: 'prefer ask_pipeworx for casual lookups.' The alternative tool is named directly, leaving no inference required.

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