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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds the useful fact that artifacts are immutable and metadata-only, but says nothing about pagination behavior for the after/limit pair or what happens when the project is inaccessible beyond the vague word 'accessible'.

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?

Two compact sentences with the scope stated first and the kind taxonomy second; no filler. The second sentence about distinct kinds is the weakest link since it gestures at the enum without helping an agent pick a value.

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?

An output schema exists, so return values need not be described, and the required project_id is named. Still, for a five-parameter, paginated, enum-heavy listing tool with 0% schema coverage, an agent needs cursor and kind guidance that the description omits.

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% across five parameters, so the description carries the full burden and only covers project_id and job_id. The large kind enum, the after cursor (pattern/maxLength suggest an opaque token) and the limit bound are never explained, leaving the most error-prone inputs undocumented.

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 gives a specific verb and resource ('List immutable artifact metadata') and scopes it to a project with an optional job restriction, which is enough to distinguish it from the single-item get_artifact sibling. It doesn't explicitly name any alternative tool, but the purpose itself is 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?

Usage context is implied by 'for an accessible project, optionally restricted to a job', so an agent can infer the primary scenario. However, there is no explicit statement of when to prefer this over get_artifact or the various list_* siblings, and no stated conditions for choosing a kind filter versus a job filter.

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