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

Annotations already establish a safe read-only, idempotent, non-destructive profile. The description adds substantial behavioral detail beyond annotations: it specifies the success return shape with evidence as verbatim quote, confidence, source, and fetched_at, and enumerates all refusal_reason values. It also discloses the extra LLM call cost and the refusal-driven 'only answer if directly supported' behavior. 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: definition, mechanism, success/refusal shapes, usage guidance, and cost comparison. It is front-loaded with the most important distinguishing trait ('Hallucination-resistant answer mode') and flows logically. Slightly long, but justified given the tool's complexity and the need to convey refusal semantics and when to prefer the cheaper sibling.

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 explains return values and failure modes, including specific refusal_reason enums. It covers routing, evidence extraction, cost, and usage boundaries. For a read-mode tool with strong annotations and a self-contained description, nothing essential is missing. An agent has enough information to select and invoke the 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?

Schema description coverage is 100%, with all six params documented as aliases for the same natural-language question. The description does not add parameter-specific detail, but the schema already fully covers the parameter semantics (accepts query, q, prompt, text, input as aliases). Baseline 3 is appropriate since the description's routing explanation adds context but no param-level meaning 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 specific, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly states the mechanism (picks the right tool, fills arguments, fetches data, extracts answer using only the tool result) and differentiates itself from ask_pipeworx by emphasizing grounded extraction and explicit refusal behavior. An agent can immediately distinguish this tool from siblings like ask_pipeworx or validate_claim.

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 (financial verdicts, legal claims, medical lookups, public statements).' It also gives a clear exclusion and alternative: 'prefer ask_pipeworx for casual lookups,' while noting the same routing as ask_pipeworx. The cost tradeoff ('Costs one extra LLM call') further informs selection.

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