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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses substantive behavior: grounded extraction, refusal semantics, refusal_reason enum values, and the exact success response shape. It also warns that it will refuse rather than invent when the data doesn't directly answer, which is critical for safe invocation.

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 well-structured and front-loaded with the core value proposition. The success/refusal contracts and usage tradeoff each earn their place, and no sentence is filler.

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?

With no output schema present, the description fully compensates by listing the success fields, refusal reasons, and cost tradeoff. It also tells the agent when the tool is appropriate and how it behaves on failure, making it complete enough to invoke 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 schema already fully documents the question parameter and aliases. The description adds no new parameter-level meaning beyond implying that the question drives tool routing and result extraction, which is already clear from 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 clearly defines the tool as a hallucination-resistant, grounded answer mode for high-stakes reads, and explicitly contrasts it with ask_pipeworx by emphasizing extraction limited to tool result contents. It states the specific behavior, output contract, and refusal conditions, making its purpose and differentiation unambiguous.

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 gives explicit guidance: use it when answers will be quoted, cited, or acted on, and prefer ask_pipeworx for casual lookups. It also identifies the extra LLM call cost as a tradeoff, giving the agent concrete criteria for choosing between the two siblings.

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