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

Annotations already declare readOnlyHint and idempotentHint, and the description materially adds behavioral detail beyond that: it returns a structured {answer, evidence, confidence, source, fetched_at, refusal_reason} object, lists all refusal reason enum values, and discloses that it costs an extra LLM call. The description complements, rather than contradicts, the 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?

Each sentence adds distinct value: mode definition, routing/extraction behavior, success output shape, refusal behavior, use cases, and cost tradeoff. It is dense but front-loaded with the most important differentiator, and no sentence 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?

For a complex grounded-answer tool with no output schema, the description fully covers the return contract, failure modes, and selection criteria. It explains what 'grounded' means operationally, names all refusal reasons, and gives sufficient context for an agent to invoke and interpret the result 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 the schema fully documenting question and all five aliases. The description references natural-language questions and argument filling, but adds no parameter-level semantics beyond the schema, so the baseline of 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 verb phrase, 'Hallucination-resistant answer mode for high-stakes reads,' and immediately distinguishes it from sibling ask_pipeworx by stating it uses the same routing but adds extraction constrained to the tool result. This lets an agent clearly identify the tool's unique role among 34 siblings.

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?

The description explicitly states when to use it ('whenever an answer will be quoted, cited, or acted on'), gives application examples (financial verdicts, legal claims, medical lookups, public statements), and explicitly says to prefer ask_pipeworx for casual lookups because of the extra LLM call. This is model usage guidance.

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