List skills

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context the annotations can't: deterministic ordering (created_at desc, id desc), deduplication/union semantics across org/project/user scopes, and the fact that grants do not affect 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, and the grant/ownership clarification is a useful closing note. Front-loading is slightly off: the least important detail (tie-break ordering) leads, while the scope/default behavior that actually selects this tool comes second.

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 no output schema, the description should describe what comes back; it hints at 'items' and their ordering but never mentions the paginated envelope (cursor/next_cursor) or the shape of returned skill records. The scoping and ordering semantics are well covered, but the return contract and pagination behavior are left unstated.

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 high (86%), so the baseline is 3, and the description earns an extra point by documenting default behavior the schema does not: omitting the owner filter yields the deduplicated union of org, project and user skills. It does not clarify sort, limit, cursor, or the glob name parameter beyond the schema.

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 a collection of skills ('returns the deduplicated union of organization skills ... project skills ... user skills'), and it distinguishes its scope from the sibling grant_skills_list by noting grants are managed separately. However, it never states the verb+resource plainly ('list skills'); it relies on the name/title for the core action and spends its text on output semantics instead.

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?

It implicitly guides usage by explaining the default behavior when no owner filter is supplied, which tells an agent how results broaden. It never states when to prefer other siblings (e.g., skills_get for a single skill, grant_skills_list for grants) or any prerequisites, so the guidance is implied rather than explicit.

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