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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive, so the safety profile is covered. The description adds substantial behavioral context beyond that: exact return shape, explicit refusal semantics with enumerated refusal_reason values, the constraint that answers must come only from tool result content, and the extra LLM call cost. This fully informs the agent about runtime behavior.

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: purpose, routing, extraction rule, return/refusal format, when to use, and cost trade-off. Key differentiators are front-loaded in the first phrase, and no filler or redundant restatement of the schema is present.

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 compensates by explicitly documenting both success and refusal return shapes. It also covers failure modes (no_tool_match, tool_error, data_truncated, etc.), which is unusual and valuable. The only required parameter is a natural-language question, and the description leaves no ambiguity about how the tool behaves in edge cases.

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 already documents the question parameter and all its aliases at 100% coverage, so the baseline for schema compensation is met. The description does not add new parameter-level semantics, but it also does not need to; the schema is sufficient. It reinforces the question-based interaction but adds no extra syntax or formatting guidance.

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 states a specific mode ('Hallucination-resistant answer mode') with a concrete resource ('high-stakes reads') and a precise behavior: extract answers using only the tool result. It explicitly distinguishes itself from ask_pipeworx by describing the same routing but an additional extraction step, so an agent can select it unambiguously.

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?

Provides explicit usage criteria: 'Use whenever an answer will be quoted, cited, or acted on' and lists concrete high-stakes domains. It also gives an exclusion rule with the alternative: 'prefer ask_pipeworx for casual lookups.' This is clear when-to-use and when-not-to-use guidance, including cost trade-offs.

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