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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses crucial behavior: it returns a structured success object with evidence as verbatim quote, and an explicit refusal object with specific refusal_reason enums. It also reveals the cost tradeoff ('Costs one extra LLM call'), providing transparency beyond what annotations cover. 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 front-loaded with its core value proposition ('Hallucination-resistant answer mode for high-stakes reads') and every subsequent sentence adds distinct information: routing scope, extraction rule, return/refusal shapes, use cases, and cost comparison. It is moderately long but has zero 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?

Given the tool's complexity (routing across thousands of tools, high-stakes use, possible refusal), the description is self-sufficient. It documents the return contract, refusal reasons, and selection criteria. With only one simple question parameter and no output schema, nothing critical 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 has 100% description coverage for the single required 'question' parameter, including aliases, so the baseline is 3. The description does not add any parameter-specific semantics; it focuses on behavior and routing, which is fine because the schema already fully documents the parameter.

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 pair ('answer mode') and precisely defines the behavior: extracts the answer using ONLY the tool result, with explicit refusal when unsupported. It clearly distinguishes itself from the sibling ask_pipeworx by highlighting the grounding/refusal mechanism and the extra LLM call.

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?

It explicitly states when to use: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' and gives concrete examples. It also states when NOT to use it: 'prefer ask_pipeworx for casual lookups,' directly naming the alternative and the condition that selects it.

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