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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does mention return fields and optional scoping, but it omits behavioral traits such as default ordering, whether results are sorted by issued_at, and whether status is filterable. The phrase 'issued certificates' is slightly ambiguous regarding whether it includes all statuses or only 'issued' status. This is a minimum-viable disclosure but lacks depth.

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, information-dense sentence that front-loads the verb and resource, lists filter options, and enumerates return fields. Every word earns its place with no redundancy 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?

For a list tool with optional filters and no output schema, the description provides essential information: return fields, filter semantics, and the list operation itself. It does not explicitly state pagination defaults or how filters combine, but the schema covers pagination and the description's 'optionally scoped' implies flexibility. Overall, it is nearly complete for common usage scenarios.

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 description adds meaning to the user_id and course_id parameters by explaining they scope results ('scoped to one user or one course'). The limit and offset parameters are not mentioned, but the schema descriptions for them are explicit (page size, rows to skip). With 50% schema coverage, the description compensates for the filter parameters, which are the core semantic aspects.

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 clearly states the action ('List issued certificates') and the resource, with optional scoping to user or course. It also enumerates return fields, distinguishing it from siblings like get_certificate and verify_certificate. The verb + resource + scoping is specific and unambiguous.

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 provides clear context for when to use the tool: listing certificates, optionally filtered by one user or one course. It does not explicitly name alternatives or exclusions, but the scoping language effectively communicates the intended use cases. Sibling names imply alternatives (e.g., get_certificate for single retrieval), but the description itself stops short of explicit when-not guidance.

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