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

Annotations already signal read-only, open-world, idempotent, non-destructive behavior; the description adds further transparency by disclosing that it only uses tool-result content, that it returns verbatim evidence or null with a specific refusal_reason, and that it costs an additional 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?

The description is dense but every clause earns its place: mode, routing, extraction rule, return shape, refusal reasons, use cases, and cost comparison are all packed into a compact paragraph with clear front-loading.

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, which it does with the success shape and refusal alternatives. Together with the annotations and sibling differentiation, an agent has everything needed to invoke and interpret this tool correctly.

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?

The schema already covers the question parameter at 100%, including aliases, so the baseline is 3. The description adds use-case context that implies the question should be verifiable, but it does not add concrete format, length, or style guidance for the question parameter beyond the schema.

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 precise verb and resource: 'Hallucination-resistant answer mode for high-stakes reads' and specifies the mechanism: it routes to the same tool pool as ask_pipeworx but extracts answers only from tool results. It differentiates from the sibling ask_pipeworx by promising verbatim evidence and explicit refusals.

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?

It gives explicit when-to-use guidance — 'whenever an answer will be quoted, cited, or acted on' and the agent must not invent facts — plus an explicit alternative preference: 'prefer ask_pipeworx for casual lookups.' The cost tradeoff is quantified as 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.