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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds the specific behavioral guarantee that it does not judge semantic choices and that it validates against a manifest and active verified catalog, providing context beyond the annotations without contradicting them.

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, front-loaded sentence that states the verb first, then the object, and then constraints. Every clause adds value: the negation clarifies scope without wasted words.

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 two parameters, no output schema, and nested objects, the description covers the core action and scope, but omits return format, failure behavior, and elaboration on domain-specific terms like 'canonical' and 'active verified catalog'. An agent would likely need additional documentation to understand the output and error handling.

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?

With 0% schema description coverage, the description partially compensates by naming 'evidence' as the selection-evidence sidecar and 'manifest' as the manifest object. However, it does not define what constitutes a canonical sidecar or the structure of the verified catalog, leaving significant ambiguity for an agent with no schema guidance.

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 the specific verb 'Validate' with a clear resource ('canonical selection-evidence sidecar') and delineates its scope by explicitly negating writing files and judging semantic choices. This distinguishes it from write-oriented siblings like export_selection_evidence and provides a crisp operational definition.

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 implies usage for read-only validation without side effects, but it does not explicitly name alternatives like export_selection_evidence or diff_stack, nor specify conditions when to prefer this tool. The 'without writing files' clause hints at a validation-only role, but exclusions are not explicit.

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