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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds materially more: it extracts answers only from tool results, returns verbatim evidence, can explicitly refuse with categorized refusal_reason values, and reveals the extra LLM call cost. There is no contradiction with 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?

The description is front-loaded with the core purpose and grows into behavioral detail, output shape, usage rationale, and cost comparison. Every sentence earns its place, and the structure makes the tool's unique value immediately visible.

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 complex routing tool with no output schema, the description thoroughly explains success and refusal return shapes, evidence behavior, applicable domains, and the relationship to ask_pipeworx. An agent has enough information to decide when to invoke it and what to expect back.

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%, with the sole required parameter 'question' fully documented along with its aliases. The description adds no new parameter-level semantics, but given the schema already handles this completely, the baseline score of 3 is appropriate.

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 a specific and distinctive purpose: a hallucination-resistant answer mode for high-stakes reads. It clearly differentiates itself from the sibling ask_pipeworx by describing its evidence-grounded extraction and explicit refusal behavior, so an agent can distinguish it without inspecting schemas.

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?

It gives explicit when-to-use guidance: use when answers will be quoted, cited, or acted on, especially for financial, legal, medical, or public-statement facts. It also names the alternative ask_pipeworx and the condition favoring it ('casual lookups'), plus 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.