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

With no annotations, the description carries the behavioral burden. It discloses that the tool takes no input, returns a well-defined structure, and is intended for a single use to branch on or validate refusals. It could be more explicit about being side-effect free, but for an introspection tool this is adequate.

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 compact and front-loads the purpose before details. The final sentence is dense, but every clause adds information about the returned structure; no filler is present.

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 no-input introspection tool with an output schema, the description is complete: it covers why to call it, what it returns, and how the refusal structure is organized. It also explains the key gap an agent might otherwise miss — that the tool's output schema covers only answers, not refusals.

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?

There are zero parameters, so there is no schema/description gap, and the description reinforces this with 'No input.' The baseline of 4 applies because no parameter documentation 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 'What a refused call looks like' and then specifies concrete outputs (`errors`, `code`, `schema`). This clearly distinguishes it from sibling introspection tools like `describe_schema`, `describe_rule`, and `describe_relations`, which cover different aspects of the API.

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 says 'use this once, to branch on refusals or validate them', giving a clear invocation condition. It does not name alternatives or state when not to use it, but the refusal-oriented purpose makes the guidance sufficient for correct selection.

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