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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, openWorldHint=true), the description richly discloses behavior: routing across 5,767 tools and 1506 sources, extraction limited strictly to tool-result content, exact success payload with verbatim evidence, and an enumerated refusal_reason set covering failure modes like not_in_source, no_tool_match, tool_error, data_truncated, and llm_error. The refusal behavior in particular is valuable context annotations could never convey.

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?

Every sentence earns its place: mode identity, routing mechanism, extraction constraint, success shape, refusal shape, usage domains, and cost tradeoff. The refusal_reason enum is the only borderline-verbose element, but it directly helps an agent handle failure gracefully. Information is front-loaded with the differentiator first.

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 present, the description fully compensates by specifying both the success and refusal return structures, including the verbatim evidence field and refusal reason taxonomy. Combined with annotations covering safety/idempotence and a 100%-covered input schema, nothing an agent needs to invoke this tool correctly or interpret its result 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 description coverage is 100% — the schema already documents 'question' as natural language with five aliases. The description adds contextual meaning (the question is routed to fill sub-tool arguments), but does not introduce parameter-level syntax or format details, so the baseline 3 for high schema coverage 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 states a specific verb+resource mode ('Hallucination-resistant answer mode for high-stakes reads') and immediately differentiates from the sibling ask_pipeworx by explaining the same routing followed by source-grounded extraction. A second sentence lays out the exact success and refusal return shapes, so an agent knows precisely what this tool is and is not.

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 given: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative (ask_pipeworx) and the condition for preferring it ('casual lookups') based on the one-extra-LLM-call cost tradeoff. Nothing is left to inference.

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