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

Discloses internal mechanics (same routing as ask_pipeworx, fills arguments, fetches data, then extracts answer only from the tool result), the success return shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}), and the full refusal contract with enumerated refusal_reason values. It adds the cost implication and receipt of verbatim evidence. This goes well beyond what annotations already convey (readOnly/idempotent), and there is 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 information-dense but every sentence earns its place: purpose, mechanism, success contract, refusal contract, usage conditions, and cost trade-off. It is front-loaded with the core differentiator and avoids repetition. Despite its length, no sentence is redundant.

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 this is a high-stakes, grounded-answer tool with no output schema, the description fully documents what the agent will receive on success and on refusal, including the exact refusal_reason enum. It also explains the relationship to ask_pipeworx and the extra cost, so the agent can make an informed routing decision. Nothing necessary for correct invocation 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 documents the 'question' parameter and its aliases (q, text, input, query, prompt) with full coverage. The description itself does not add parameter-specific semantics, but the schema carries the burden effectively. Since coverage is 100%, a baseline score of 3 is appropriate per the rubric; no further compensation is needed.

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 verb and resource: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly differentiates from sibling ask_pipeworx by emphasizing that the answer is extracted using ONLY what the tool result contains and by exposing the refusal mechanism. An agent can immediately identify what this tool does and how it differs from its sibling without opening 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?

Provides explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also gives a concrete when-not-to-use case: 'prefer ask_pipeworx for casual lookups.' The alternative tool is named explicitly, and the cost trade-off (one extra LLM call) justifies the choice. This is textbook usage differentiation.

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