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

Beyond the readOnly/idempotent annotations, the description discloses the grounding mechanism: answers are extracted using ONLY the tool result, and it enumerates the exact refusal reasons when the data doesn't directly answer. The extra LLM call cost is also a transparent behavioral trait not visible 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?

Each of the five sentences earns its place: mode definition, routing mechanism, return shape, usage trigger, and cost trade-off. The purpose is front-loaded, and there is no filler or repetition of schema fields.

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 specifies both the success return object and the refusal return object with all refusal_reason enum values. It also covers the alternative tool and the selection condition. An agent has everything needed to invoke this tool 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 input schema already documents the question parameter and aliases with 100% coverage, so the baseline is 3. The description adds meaningful context by explaining that the question drives routing and argument-filling across 5,743 tools, which tells the agent how the parameter is actually used beyond a simple string.

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 opens with a specific purpose: a 'hallucination-resistant answer mode for high-stakes reads' and then details the full pipeline from routing to extraction. It explicitly differentiates from the sibling 'ask_pipeworx' by positioning this as the grounded alternative and mentioning the trade-off ('prefer ask_pipeworx for casual lookups').

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 and specifies when to choose it ('prefer ask_pipeworx for casual lookups'), leaving no ambiguity about selection.

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