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 does not contradict these — it actually reinforces them ('fetches the data', 'using ONLY what the tool result contains'). Beyond the annotations, it discloses substantial behavior: the exact success return shape with verbatim evidence quote, the explicit refusal mode with the full refusal_reason enum, and the cost tradeoff of one extra LLM call. This is far more behavioral context than the annotations alone provide.

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 a dense ~110-word paragraph where every sentence earns its place: mode, routing, extraction behavior, return shape, refusal semantics, use cases, and cost tradeoff. The key differentiator is front-loaded in the first phrase. It is long, but the tool is complex and the length is justified; the main structural weakness is that the success/refusal shapes and enum values are packed inline, making them harder to parse than if separated.

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 complex, high-stakes tool with no output schema, the description is unusually complete: it explains the return value explicitly (success and refusal shapes with all refusal_reason values), the grounding constraint, when to use it versus the cheaper sibling, and the operational cost caveat. Nothing an agent needs to decide whether to call it, or to interpret its result, 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 schema already documents the question parameter and its aliases (query, q, prompt, text, input), establishing the baseline of 3. The description adds no parameter-level meaning beyond mentioning that the tool 'fills arguments' during routing, which only weakly implies the user supplies the question in natural language. It doesn't compensate for or contradict the schema, but it also doesn't need to given full coverage.

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 clear, specific verb+resource+mode: 'Hallucination-resistant answer mode for high-stakes reads.' It states exactly what the tool does — routes to the matching source tool, fetches data, and extracts an answer using only the tool result. It also distinguishes itself from the sibling ask_pipeworx by naming it directly ('Same routing as ask_pipeworx') and by its grounded evidence-extraction behavior, so an agent can tell them apart 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?

Explicit when-to-use guidance is provided: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete examples (financial verdicts, legal claims, medical lookups, public statements). It also gives an explicit exclusion and alternative: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This names the sibling alternative and the condition that selects it, leaving nothing to inference.

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