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

Beyond annotations, it reveals the return shape on success and failure, specific refusal_reason enum values, and the guarantee that answers are extracted only from tool results. It also discloses the extra LLM-call cost, which agents can use for planning. No contradiction with readOnlyHint, openWorldHint, or idempotentHint.

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 carries distinct load: purpose, routing mechanics, response/refusal contract, use cases, and cost trade-off. The length is justified by the behavioral complexity and there is no filler.

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 tool with no output schema, the description fully equips an agent: when to use, what it returns, what refusal looks like, and when to use the sibling instead. Combined with complete schema coverage, nothing needed to call it 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?

The input schema provides full descriptions for all parameters, including alias behavior for question, so the description need not add parameter detail. It doesn't add any param-specific meaning beyond what the schema already states, so a baseline 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 names a specific mode ('Hallucination-resistant answer mode for high-stakes reads') and an explicit operation: route to a tool, fetch data, then extract an answer using only the tool result. It also distinguishes itself from ask_pipeworx by promising evidence and refusal behavior rather than a casual answer.

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 an explicit trigger: use when an answer will be quoted, cited, or acted on, and when the agent must not invent facts, with concrete domains like financial verdicts, legal claims, medical lookups, and public statements. It also states the exclusion: prefer ask_pipeworx for casual lookups, and quantifies the cost trade-off ('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.