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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. Beyond that, the description adds genuinely useful behavior: deterministic ordering (created_at desc, then id desc), deduplication across three ownership scopes, permission-bounded visibility ('the caller may list'), and the fact that grants are orthogonal to ownership.

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 tight sentences with no filler, each carrying distinct information (ordering, default scope, grant independence). It is front-loaded with a secondary detail (ordering) rather than the primary purpose, but nothing is 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?

With 7 parameters at full schema description coverage and no output schema, the description covers the non-obvious parts of the contract: ordering, deduplication, and visibility scoping. Pagination behavior is left to the cursor/limit schema fields, which is acceptable, though it does not describe the shape of returned items.

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 100%, so the baseline is 3, but the description adds semantics the schema does not: what happens when no owner filter is supplied (the deduplicated union) and that owner_kind reflects an immutable owner, clarifying the meaning of the enum beyond its label.

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 conveys that this returns skills (the union of org, project, and user skills) and the title supplies the verb 'List'. It also signals separation from grant-related surfaces via 'Grants are managed separately', giving some sibling differentiation against grant_skills_list, but it never names skills_get or explains the list-vs-get distinction.

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 clause 'Without an owner filter, returns the deduplicated union...' implies that owner_kind/owner_project_id narrow the result, and 'Grants are managed separately' steers the agent away from grant listing. However, there is no explicit when-to-use statement or call-out of the alternative tools (skills_get, grant_skills_list) that an agent would weigh.

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