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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds substantial behavioral context: it explains the extraction pipeline, the one-extra-LLM-call cost, the exact success return shape, and the structured refusal reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). This fully informs the agent about edge-case behavior without contradicting any annotation.

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 information-dense but every clause earns its place: purpose, routing behavior, safety guarantee, return format, refusal reasons, use cases, and cost trade-off. Critical scoping information is front-loaded ('Hallucination-resistant... high-stakes reads') and the cost/alternative guidance comes last as a natural decision aid.

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?

Despite having no output schema, the description fully specifies the success and refusal return shapes. It covers cost trade-offs, routing behavior, when to use, when not to use, and the alternative tool. For a tool with only one required parameter and complete schema coverage, nothing an agent needs to invoke it correctly 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?

Schema coverage is 100%: the schema documents the 'question' field and all five aliases. The description does not add parameter-level detail, but it does not need to. Baseline 3 is appropriate because the schema carries the full parameter burden and the description adds no conflicting or additional semantics.

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, differentiated purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It names the sibling tool it builds on ('Same routing as ask_pipeworx') and explains the difference: it extracts answers using only tool-result content. This gives an agent a clear, specific verb and resource, and distinguishes it from the closely named ask_pipeworx.

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 explicitly states when to use this tool ('whenever an answer will be quoted, cited, or acted on... must not invent facts'), gives example domains (financial verdicts, legal claims, medical lookups, public statements), and explicitly directs casual lookups to the cheaper alternative: 'prefer ask_pipeworx for casual lookups.' That is exemplary usage guidance with both inclusion and exclusion.

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