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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint; the description adds substantial behavior beyond those: the exact success return shape with verbatim evidence, the full refusal_reason enum (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), and the extra-LLM-call cost tradeoff. The refusal behavior is a critical disclosed trait an agent must know before invoking. No contradiction with 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 and somewhat long, but every sentence earns its place: the differentiator is front-loaded, the return/refusal shapes are compressed into compact JSON literals, and the cost tradeoff is one clause. Slightly heavy due to the enumerated refusal enum and example domains, but not wasteful.

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?

Given there is no output schema, the description correctly takes on the burden of documenting the return shape and the full refusal_reason set — both present. Combined with a single documented parameter, rich annotations, and explicit sibling differentiation, 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 already documents the question parameter and all six aliases with a clear description. The tool description adds no parameter-level meaning beyond that; it focuses on mode behavior instead. Per the baseline rule for high schema coverage, 3 is appropriate: the schema carries the burden adequately.

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?

Opens with a specific, differentiated claim — 'Hallucination-resistant answer mode for high-stakes reads' — and a precise verb+resource: answer a natural-language question by routing to the best tool and extracting the answer grounded in the tool result. It explicitly distinguishes itself from the sibling ask_pipeworx, so an agent can tell them apart 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?

Gives explicit when-to-use criteria ('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 states the exclusion condition ('prefer ask_pipeworx for casual lookups'), leaving nothing to inference.

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