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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses the exact success return shape, the explicit refusal contract with enumerated refusal_reason values, and the grounding behavior of using only tool-result content. It also discloses the extra LLM call cost, which is useful behavioral context not present in 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 yet compact, front-loading the core purpose before explaining routing, return contract, refusal behavior, and usage guidance. Every sentence contributes value, and the preferential routing note is placed at the end without cluttering the main point.

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?

Despite having no output schema, the description specifies exactly what is returned on success and on refusal, including field names and possible refusal reasons. It also provides routing context, source scale, and the practical cost trade-off, making the tool fully usable by an agent without further inference.

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 single meaningful parameter 'question' fully documented in natural language, so the baseline is 3. The description adds context about high-stakes use but does not need to explain the parameter further.

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, grounded answer mode and contrasts it with ask_pipeworx by emphasizing extraction solely from tool results. It names the verb-like behavior (answer, refuse, return evidence) and the resource scope (5,908 tools across 1,540 sources), making it easy to distinguish 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?

The description explicitly states when to use this tool: whenever an answer will be quoted, cited, or acted on and fact invention is unacceptable. It also gives a clear alternative preference, saying to prefer ask_pipeworx for casual lookups because this mode 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.