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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral details beyond those: the refusal mechanism with specific refusal_reason values, the guarantee of using only tool result content, and the extra LLM call cost. These are not implied by annotations and are essential 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 front-loaded with the core purpose and differentiator, then details the return contract and refusal modes, and ends with a cost/usage hint. Every sentence carries meaningful operational information—no fluff or repetition of schema.

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?

Given the tool's complexity (refusal logic, structured return object, extra LLM cost) and the absence of an output schema, the description fully explains the success and failure return shapes, the refusal reasons, and the use-case criteria. An agent has everything needed to call and interpret results 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?

The schema covers 100% of parameters (all aliases for 'question' are described). The description adds only a generic note that 'question' is natural language, which the schema already states. Since the schema does the heavy lifting, a baseline 3 is appropriate; no additional semantic depth is provided.

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 states a specific verb+resource: 'Hallucination-resistant answer mode for high-stakes reads.' It explicitly differentiates from the sibling 'ask_pipeworx' by the extra extraction step and refusal behavior, making the distinction 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?

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 ('prefer ask_pipeworx for casual lookups') and gives a cost tradeoff (one extra LLM call), so an agent can route correctly.

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