cleanup_skill

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: it discloses that canonical content is preserved, that targets lacking suitable managed manifests are blocked, that no cleanup snapshot is created and sync_skills is the recovery path, and that the targets flag is inert. That is exactly the operational context an agent needs before invoking a destructive tool.

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?

The description is front-loaded with purpose and alternatives, then caveats, then return/restore information — a sensible ordering and dense with signals. It is somewhat long and partially duplicates the schema's parameter text, but no sentence is empty.

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 destructive, three-parameter tool with an output schema, it covers purpose, alternatives, prerequisites, destruction scope, the no-snapshot caveat, recovery path, and named return fields (plan, removed_paths, warnings). Nothing an agent needs in order to call this safely is missing.

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 dry_run, targets, and skill_id_or_name are already documented in the schema with the same semantics the description restates. The description adds only the accepted identifier forms (ID, slug, unambiguous name) and the latent-candidate exclusion, which is marginal value over 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 names a specific verb (preview or remove) and resource (managed native copies for one active canonical skill), and explicitly scopes it as 'one active canonical skill' rather than project-wide. An agent can distinguish it from repair_skills and deactivate_skill without opening any schema.

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 states when to use this tool ('cleaning that skill's installed runtime copies') and names both alternatives with the condition that selects them: repair_skills for orphan targets across the project, deactivate_skill for latent candidate state. Prerequisites (initialized project memory, resolvable skill identifier) are also given.

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