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

Beyond the readOnly/openWorld/idempotent annotations, the description exposes important behavior: extraction uses ONLY the tool result, refusal is explicit, refusal_reason has a defined enum, evidence is a verbatim quote, and it costs one extra LLM call. These details substantially exceed what annotations already provide.

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 front-loaded, starting with the core distinction and flowing through behavior, return shape, use cases, and cost. Every sentence contributes value, though the long first sentence and embedded refusal-reason list make it heavier than necessary.

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 compensates by specifying the success return object and the exact refusal_reason values. It also covers when to use, how it differs from ask_pipeworx, cost, and safety-related behavior, so an agent has enough context to invoke it 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%, and the schema already explains the `question` field and its five aliases. The description only says routing 'fills arguments' and does not add parameter-level meaning. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 'Hallucination-resistant answer mode' and immediately contrasts this tool with ask_pipeworx, making the core purpose unmistakable. It identifies the resource (Pipeworx), the action (routing, extraction, refusal), and clearly distinguishes this sibling from the non-grounded variant.

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?

It gives explicit selection criteria: 'Use whenever an answer will be quoted, cited, or acted on' and lists concrete high-stakes domains. It also provides a negative rule with a cost tradeoff: 'prefer ask_pipeworx for casual lookups.' This gives the agent both when-to-use and when-not-to-use guidance.

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