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

Annotations already mark it read-only, idempotent, and non-destructive. The description adds observable behavior: newest-first ordering, every entry carrying the producing revision, and recovery of lost artifact ids without walking jobs_list.

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?

Three sentences, each carrying distinct information: what the tool lists, why revision info matters, and where download URLs live. No filler or restatement of the title.

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 read-only list tool with an output schema, the description supplies key selection criteria, ordering, filter options, and the sibling relationship. Pagination is left to the schema's cursor field, which is acceptable given the output schema exists.

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 coverage is 100%, so the schema already documents projectId, kind, limit, cursor, and revisionId. The description adds only high-level filter and ordering context, which is useful but not needed to compensate for missing parameter docs.

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 action ('List a project's artifacts'), scopes it to a project, and specifies ordering ('newest-first') and supported artifact kinds. It also distinguishes itself from artifact_get by noting that download URLs live there.

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?

Names artifact_get as the source for download URLs and jobs_list as a heavier alternative for recovering artifact ids, giving an agent clear routing cues. This is explicit enough to choose this tool over siblings without opening their schemas.

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