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

Annotations already declare read-only, open-world, idempotent, and non-destructive hints. The description adds significant behavioral detail: it extracts only from the tool result, returns a structured success or refusal shape with specific refusal_reason values, and mentions the extra LLM cost. This goes well beyond the 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?

The description is dense but well-structured, front-loading the core purpose and then covering behavior, usage, and cost. It is appropriately detailed for the tool's complexity; no sentence is wasted, though it is longer than typical.

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 tool with no output schema, the description fully compensates by specifying the exact success and refusal return shapes, including evidence and refusal reasons. It also covers routing scope and cost, making it complete for an agent to call 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 coverage is 100% – all 8 parameters are aliases for 'question' and are described in the schema. The description adds no additional parameter-level meaning beyond that, so the baseline of 3 applies.

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 purpose: hallucination-resistant answer extraction for high-stakes reads. It distinguishes itself from the sibling ask_pipeworx by explicitly describing the grounded extraction mode, so an agent can differentiate between them without opening schemas.

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 ('whenever an answer will be quoted, cited, or acted on') and when-not-to-use ('prefer ask_pipeworx for casual lookups'), including a cost trade-off (one extra LLM call). This leaves 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.