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

Annotations already establish read-only, idempotent behavior, but the description adds substantial non-obvious context: it refuses rather than guesses, returns verbatim evidence, and enumerates exact refusal reasons. It also discloses the performance/cost implication of an extra LLM call. No contradiction with 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 information-dense but not bloated. Every segment earns its place: the mode label, routing mechanism, extraction rule, return contract, refusal reasons, use cases, and cost trade-off. It is front-loaded with the core differentiator.

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?

Even without an output schema, the description fully specifies both the success payload and the refusal payload, including possible refusal_reason values. It also covers scope, grounding behavior, and when to choose the sibling tool, leaving no critical operational gap.

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 already defines the question parameter and all aliases clearly. The description adds no parameter-specific semantics beyond the schema, so the baseline score of 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 states a specific mode — hallucination-resistant, grounded answering — and explains that it routes through the same machinery as ask_pipeworx but extracts answers only from tool results. It directly distinguishes itself from the sibling ask_pipeworx, making the tool's specialty clear.

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?

Explicitly says to use this tool when answers will be quoted, cited, or acted on and when invention is unacceptable. It also gives a concrete exclusion rule: prefer ask_pipeworx for casual lookups because this tool costs an extra LLM call.

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