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

The description goes well beyond the annotations by detailing refusal behavior, refusal_reason enum values, evidence as verbatim quote, and the grounding mechanism that only uses tool result content. It also discloses the extra LLM call cost, which is important operational behavior. No contradiction with the readOnly/openWorld/idempotent hints.

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 efficient, front-loading purpose, then output shape, then usage guidance, then cost tradeoff. Every sentence contributes meaningful information, though the single paragraph format is slightly heavier than necessary and could benefit from bullets.

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 grounded question-answering tool with no output schema, the description fully covers when to use it, what it returns, how it refuses, and when not to use it. The cost comparison and explicit refusal reasons provide the agent with all needed context for correct invocation and interpretation.

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 describes the question parameter with aliases, and schema description coverage is 100%. The description adds high-level context about routing across 5,908 tools and filling arguments, but it does not need to restate parameter semantics; 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 clearly identifies this as a 'hallucination-resistant answer mode' for high-stakes reads, distinguishes it from ask_pipeworx, and specifies its grounded extraction behavior. The verb 'extracts' plus the explicit output and refusal shapes make the tool's purpose unambiguous even next to similar 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?

The description explicitly states when to use this tool: when answers will be quoted, cited, or acted on and facts must not be invented. It also provides a clear exclusion: prefer ask_pipeworx for casual lookups, and explains the cost tradeoff of 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.