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

Beyond the readOnly/idempotent annotations, the description discloses the refusal behavior, exact success and refusal response shapes, refusal reasons, and the extra LLM call cost. It directly addresses hallucination risk by stating the answer is extracted using ONLY what the tool result contains, which is valuable behavioral context.

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 core mode and primary behavior are front-loaded, and every sentence adds meaningful information: routing, extraction constraint, output contract, refusal conditions, usage guidance, and cost trade-off. It is dense without being redundant.

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?

There is no output schema, so the description's explicit return contract and refusal reason enum are necessary and sufficient. It also covers cost, relationship to ask_pipeworx, and safe usage contexts, making the tool complete for selection and invocation.

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 has 100% description coverage and clearly documents the question parameter plus aliases. The description does not need to re-explain parameters; it adds pipeline context but no additional parameter semantics beyond the schema.

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 mode—'Grounded'—and its defining behavior: being hallucination-resistant and extracting answers using ONLY the tool result. It clearly distinguishes itself from the sibling ask_pipeworx with 'Same routing as ask_pipeworx' and the contrast between grounded extraction and casual lookups.

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 states explicit when-to-use conditions: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with high-stakes examples. It also provides the alternative and trade-off: 'prefer ask_pipeworx for casual lookups' and 'Costs one extra LLM call vs ask_pipeworx.'

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