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

Beyond annotations, the description richly discloses behavior: refusal reasons are enumerated, return shape is specified, and it explicitly notes the extra LLM call cost and the promise to use 'ONLY what the tool result contains.' This gives the agent accurate expectations about success and failure modes. No contradiction exists with the readOnly/openWorld/idempotent 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-organized: it front-loads the core distinction ('Hallucination-resistant answer mode'), then details the mechanism, return contract, refusal reasons, use cases, and cost tradeoff. Every clause earns its place and there is no filler. The structure keeps critical decision factors near the beginning.

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 success response fields and all refusal_reason values. It also covers the relationship to ask_pipeworx, the cost implication, and the high-stakes contexts where this mode is warranted. An agent has everything needed to select and invoke the 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?

Schema description coverage is 100%: the single meaningful property, question, is fully documented with aliases. The tool description adds no new parameter-level semantics, which is acceptable because the schema already carries that burden. Baseline 3 is appropriate here.

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 states a specific verb and resource: it is an answer mode that 'EXTRACTS the answer using ONLY what the tool result contains,' and it clearly distinguishes itself from sibling ask_pipeworx by emphasizing grounded, hallucination-resistant behavior. The phrase 'Same routing as ask_pipeworx' also frames exactly what this variant adds, so an agent can differentiate it without inspecting the schema.

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 gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete examples like financial verdicts and legal claims. It also states when NOT to use it: 'prefer ask_pipeworx for casual lookups' and cites the cost tradeoff of 'one extra LLM call.' This is exemplary routing guidance.

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