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

The description goes well beyond the annotations by disclosing exactly what happens on success and on refusal: it returns {answer, evidence, confidence, source, fetched_at, refusal_reason:null} or an explicit refusal with enumerated refusal_reason values. It also reveals the extra LLM call cost and the grounding constraint ('using ONLY what the tool result contains'), which are meaningful behavioral traits 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 dense but every clause earns its place: it states purpose, routing, extraction behavior, return shape, refusal reasons, usage scenarios, and cost trade-off. The structure front-loads the core distinction and then supports it with concrete examples and an explicit recommendation about the cheaper alternative.

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 tool with no output schema, the description fully explains success and failure return contracts including specific refusal_reason enums. It also addresses the tool's complexity (routing across 5,724 tools) and provides cost guidance, making it complete enough for an agent to invoke and interpret the response correctly.

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%, so the input schema already documents that all six parameters are aliases for a natural-language question. The description does not add parameter-specific semantics beyond restating that the input is a question, but as baseline with full schema coverage, a score of 3 is appropriate because the schema carries the burden.

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 answer mode') tied to a concrete resource ('ask_pipeworx' routing) and clearly differentiates itself from ask_pipeworx by emphasizing extraction from tool results only. The title 'Grounded' reinforces the distinction, and the description explicitly contrasts with the sibling tool by naming the extra extraction step and refusal behavior.

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 whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete examples (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative (ask_pipeworx) and even provides a preference rule based on cost, making the selection decision unambiguous.

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