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

Annotations already provide read-only, non-destructive, idempotent signals, and the description adds rich behavioral detail: exact success payload shape, explicit refusal reasons, verbatim evidence extraction, and the extra LLM call cost. It does not contradict 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?

Every sentence earns its place: purpose, mechanism, return contract, usage context, and cost/alternative. The structure front-loads the core identity and avoids filler or redundancy.

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?

Given there is no output schema, the description appropriately documents the complete success and refusal response shapes, including the refusal_reason enum values. Combined with the fully covered parameter schema and explicit sibling comparison, nothing needed for correct invocation 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?

Schema description coverage is 100%, and the schema fully documents the single required question parameter and its aliases. The description adds no parameter-level detail, but the schema already carries that burden adequately.

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 'Hallucination-resistant answer mode for high-stakes reads,' clearly defining the tool as a specific grounded answer mode. It also distinguishes itself from ask_pipeworx by explaining that it 'EXTRACTS the answer using ONLY what the tool result contains,' making sibling differentiation explicit.

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 provides 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 gives a clear preference rule: 'prefer ask_pipeworx for casual lookups.'

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