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

Annotations already mark readOnly/openWorld/idempotent, and the description adds substantial behavioral context: it uses only tool-result content, returns verbatim evidence, exposes a structured refusal_reason enum, and costs an extra LLM call. 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 key differentiator is front-loaded, followed by the return contract, use cases, and cost trade-off. Every sentence adds operational value without padding or tautology.

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?

For a tool with no output schema, the description fully spells out success and refusal shapes, when to prefer it, the extra cost, and the safety behavior. An agent has everything needed to decide and invoke it 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?

The input schema covers 100% of the parameter (question plus aliases), so the description doesn't need to repeat parameter meaning. The description adds no extra parameter-level detail, but the schema already handles that 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?

States a specific verb and purpose: a hallucination-resistant answer mode that routes through the same 5,798-tool set as ask_pipeworx but extracts answers solely from tool results. It clearly distinguishes itself from ask_pipeworx by emphasizing grounded extraction and explicit refusals.

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?

Explicitly says when to use it (high-stakes reads, answers that will be quoted/cited/acted on, domains where invention is unacceptable) and when not to use it (casual lookups, prefer ask_pipeworx). It names the alternative directly and gives a concrete trade-off.

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