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

The description goes well beyond the readOnly/openWorld/idempotent annotations by detailing the refusal contract, exact return fields, and failure reasons. It fully discloses that the tool may return null answer with a refusal_reason rather than guessing, which is critical behavioral context for an agent.

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 adds value: behavior, return contract, use cases, and cost tradeoff are all covered without repetition. Core positioning is front-loaded before the detailed return format.

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-question tool with no output schema, the description fully compensates: it specifies exact success and refusal shapes, all refusal reasons, routing behavior, and selection criteria. An agent has everything needed to invoke and interpret the result.

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% and every parameter is an alias for 'question' with its own description. The tool description adds no parameter-specific semantics, but the schema already carries full meaning, so the baseline 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?

The description names a specific behavior: hallucination-resistant answer extraction for high-stakes reads, and explicitly contrasts it with ask_pipeworx. It clearly states what data is used (only the tool result) and what the tool returns, so an agent can distinguish it from 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?

Provides explicit when-to-use guidance: when answers will be quoted, cited, or acted on and facts must not be invented. It also gives a clear alternative preference, ask_pipeworx for casual lookups, and states the cost tradeoff (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.