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

The description discloses the full success/refusal return contract, including specific refusal_reason values, and explains the extra LLM call and grounding behavior. This goes well beyond the annotations by describing failure modes and output structure, especially important with no output schema.

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?

Dense but well organized: purpose, behavioral guarantee, routing, output shape, refusal reasons, usage guidance, and cost trade-off all appear without filler. The most decision-relevant information is front-loaded.

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 read-only grounding tool with no output schema, the description fully compensates by specifying the answer object, refusal reasons, when to use it, and when to prefer the sibling. An agent has enough information to invoke it correctly and interpret its results.

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 already documents the question parameter and all aliases with 100% coverage, including a description on each alias. The tool description does not add new parameter-level detail, but it does not need to given the schema's completeness.

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?

Clearly describes itself as a hallucination-resistant answer mode for high-stakes reads, with a specific verb-like function and resource scope. It explicitly distinguishes itself from ask_pipeworx by explaining that it extracts answers only from tool results, while using the same routing.

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?

States exactly when to use: when answers will be quoted, cited, or acted on and hallucination is unacceptable. It also names the alternative (ask_pipeworx) and explicitly advises preferring it for casual lookups, plus flags the extra LLM call cost.

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