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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses the full behavioral contract: on success it returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null}, and on insufficient data it returns a structured refusal with enumerated refusal_reason values. It also reveals the internal mechanism ('fills arguments, fetches the data') and the extra LLM call cost.

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 the defining characteristic, followed by mechanism, return shape, usage guidance, and cost tradeoff. Every sentence adds distinct value; the length is justified by the richness of the tool contract and there is no repetition or 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?

Even without an output schema, the description enumerates the exact success and refusal response structures, covers all likely failure modes (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), and gives routing guidance vs ask_pipeworx. This is complete enough for an agent to invoke and interpret the tool correctly.

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%, so the baseline is 3. The description adds context beyond the schema by explaining that the tool internally picks the right tool and fills arguments, which tells the caller that the single question parameter is all they need to provide. This is a useful semantic clarification even though the schema already describes the aliases.

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+resource: 'Hallucination-resistant answer mode for high-stakes reads.' It then explicitly contrasts with ask_pipeworx ('Same routing as ask_pipeworx' but 'EXTRACTS the answer using ONLY what the tool result contains'), cleanly distinguishing it from the sibling tool. This is the clearest possible answer to what the tool does and how it differs.

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?

The description states exactly when to use it: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' and gives concrete high-stakes examples. It also provides the alternative condition: 'prefer ask_pipeworx for casual lookups,' naming the sibling and the cost tradeoff.

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