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

Annotations already mark this read-only, open-world, idempotent, and non-destructive, and the description adds substantial behavior beyond that: explicit refusal reasons, evidence as a verbatim quote, and the extra LLM call cost. It also discloses failure modes such as 'not_in_source' and 'data_truncated,' which is valuable behavioral context. No contradiction with annotations exists.

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 but every sentence earns its place: purpose, return shape, refusal behavior, usage guidance, and cost comparison. The most important differentiator, hallucination resistance, is front-loaded, and the alternative routing hint is integrated naturally rather than as a separate afterthought.

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?

This is a complex tool with routing across thousands of sources and no output schema, so the description must carry the return-value burden. It fully specifies both success and refusal response shapes, including refusal reason enums. It also covers cost/performance tradeoffs and usage boundaries, making it complete for correct invocation.

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%, and the schema already fully explains the single required parameter, its aliases, and its natural-language form. The description adds no additional parameter semantics, so the baseline of 3 is appropriate.

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 clearly distinguishes itself from ask_pipeworx by explaining that it uses the same routing but extracts the answer using ONLY what the tool result contains. An agent can immediately tell this is the grounded, evidence-bound variant.

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?

Usage conditions are explicit: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete examples like financial verdicts, legal claims, and medical lookups. It also names the alternative preference: 'prefer ask_pipeworx for casual lookups.' No inference is needed.

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