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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the specific data scope (agency explanation, named restriction references, source evidence, supported business links), which is useful context beyond just 'retrieve'. However, it does not disclose other behavioral aspects like error handling, pagination, or the meaning of the 'generation' parameter. Since annotations cover the main safety and the description adds some context, a 3 is appropriate.

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 a single, efficient sentence that front-loads the action ('Retrieve an exclusion') and then lists the content components without any filler. Every clause contributes value, and the structure is clear and scannable. No waste.

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?

The tool has two parameters (one required) and no output schema. The description lists the data components that will be returned, giving some idea of the output structure, but it does not explain the parameters or clarify the role of 'generation'. Without an output schema, an agent must rely on the description to understand the response, and while the component list helps, it is not enough to fully prepare an agent to call the tool correctly, especially given the lack of parameter semantics. A 3 is appropriate for a retrieval tool with this level of ambiguity.

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 0%, meaning neither 'id' nor 'generation' has any documentation in the schema. The description does not explain either parameter; it only implies through the tool name that 'id' identifies the exclusion, but it never states that explicitly. The 'generation' parameter is completely unexplained. With zero schema coverage, the description carries the full burden for parameter semantics but fails to compensate.

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 ('Retrieve') and resource ('an exclusion') and enumerates the exact data components returned (agency explanation, named restriction references, source evidence, supported business links). This is clearer than a generic 'get' but does not explicitly differentiate from siblings like 'detail' or 'document', which might also retrieve similar content.

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 offers no guidance on when to use this tool versus the many siblings (e.g., check_exclusions, explain_match, detail). It does not state any conditions, exclusions, or alternatives. An agent would have to infer the intended use solely from the name and the data list, which is insufficient given the tool's position among 11 siblings.

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