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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses the exact refusal contract with enumerated refusal_reason values, the evidence verbatim-quote behavior, and the cost implication. This tells the agent what happens when the data does not directly answer.

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?

Dense but every sentence earns its place: purpose, routing behavior, output shape, refusal modes, use cases, and cost tradeoff. The first sentence is slightly long, but it front-loads the most important decision-relevant information.

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 single-required-parameter tool with complete schema coverage and rich annotations, the description supplies the return shape, refusal semantics, use cases, and cost comparison. Nothing critical is missing for an agent to select and invoke it 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 coverage is 100%, with all six parameters documented as aliases for the single natural-language question field. The description adds no parameter-specific detail, so the baseline of 3 applies.

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?

States it is a 'Hallucination-resistant answer mode for high-stakes reads' and explicitly contrasts it with ask_pipeworx by name ('Same routing as ask_pipeworx'). It also defines the distinct output contract and refusal behavior, making it easy to differentiate from sibling tools.

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?

Gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also names the alternative and the tradeoff: 'prefer ask_pipeworx for casual lookups' and notes the extra LLM call cost.

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