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

Beyond the annotations, the description discloses the tool's refusal mechanism and the exact refusal_reason enumeration ('not_in_source','no_tool_match','tool_error','data_truncated','llm_error'), the evidence field as a 'verbatim quote', and the guarantee that extraction uses 'ONLY what the tool result contains.' It also documents the cost difference versus ask_pipeworx. No annotation contradiction exists.

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 sentence earns its place: a tagline, a mechanism summary, return/refusal shapes, usage cases, and the cost tradeoff. The beginning front-loads the differentiator ('Hallucination-resistant answer mode') before any mechanism or schema detail. While dense, it is efficiently organized with no filler.

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?

The description fully compensates for the absent output schema by specifying exact success and refusal JSON shapes, including example values for refusal_reason. It covers the open-world refusal behavior, the cost tradeoff, and routing relationship to ask_pipeworx, so nothing an agent needs to select and invoke the tool is missing.

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 all six parameters with 100% coverage, so the baseline is 3. The description adds no param-specific semantics beyond 'Your question in natural language', which also appears in the schema's question description. The alias list is fully captured in the schema, so the description adds nothing further.

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 function: 'Hallucination-resistant answer mode for high-stakes reads' and explains the mechanism — same routing as ask_pipeworx, then extraction of an answer using only tool results. It clearly distinguishes the tool from the sibling ask_pipeworx by focusing on grounded extraction with refusal behavior, and from other siblings by naming its purpose.

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?

Explicit when-to-use guidance is present: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements).' It also names the alternative and gives a clear preference: 'prefer ask_pipeworx for casual lookups,' supported by the cost tradeoff of 'one extra LLM call.'

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