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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral context: results are ordered by most recent update, archived projects are omitted by design, and the call is free ("$0"). It still doesn't state pagination behavior beyond the schema's limit, which keeps it from a 5.

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?

Compact and front-loaded: purpose and returned fields come first, then filtering, then the archived exclusion, then cost. The parenthetical asides ("the answer glosses", the trailing "$0.") add some noise and awkwardness but no sentence is truly wasted.

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 annotations carrying the safety profile and no output schema, the description supplies fields, ordering, filters, default exclusions, and cost. Only minor gaps remain, such as result-size/pagination behavior when the limit is exceeded.

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 baseline is 3, but the description adds value the schema lacks: concrete example status values (EDITORIAL_BLOCKED, STUDIO_READY, FINAL_REVIEW, PUBLISHED) for a parameter with no enum defined, plus a scope note (100+ projects). The phrasing "one of the `statuses` the answer glosses" is circular, but the examples 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?

States a specific verb+resource (list the caller's organization's projects) and enumerates returned fields plus default ordering, which is more than a bare restatement. It does not explicitly contrast itself with sibling readers like get_project_status or list_versions, but the scope 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?

Filter behavior for `status` and `q` is described, and the caller learns archived projects are excluded by design, which implies when results are relevant. However, there is no explicit guidance on when to prefer this tool over siblings such as get_project_status or list_cast, so usage is only implied.

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