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

The description discloses significant behavioral detail beyond annotations: it only uses tool result content, returns a structured success object with evidence and confidence, and can explicitly refuse with enumerated refusal reasons. It also surfaces the cost tradeoff of one extra LLM call. These behaviors are not conveyed by the readOnly/openWorld/idempotent annotations, so the description adds substantial transparency.

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?

Every sentence in the description earns its place: core purpose, routing mechanism, success response shape, refusal response shape, use cases, and cost comparison are all packed in without redundancy. The structure is front-loaded with the critical 'hallucination-resistant' identity and flows logically.

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, the description fully documents both success and refusal return formats, which is essential for an agent to interpret the result correctly. It also explains when to prefer the sibling, what kinds of questions are appropriate, and the cost consequence, making the description self-sufficient for correct invocation and response handling.

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 for the single real parameter, question, including aliases, so the description need not restate parameter syntax. The description does add context about how the question is routed and used, but no additional parameter-specific detail is necessary. Baseline 3 is appropriate because schema carries the load.

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 the tool as a 'hallucination-resistant answer mode for high-stakes reads' with a specific mechanism: it routes a query through 5,798 tools and extracts answers only from the returned data. It distinguishes itself from the sibling ask_pipeworx by emphasizing grounded extraction and refusal behavior, making the purpose and differentiation unmistakable.

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 provides explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also names the alternative ask_pipeworx and gives a clear when-not-to-use rule: 'prefer ask_pipeworx for casual lookups,' justified by 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.