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

Annotations declare destructive=true and idempotent=true, and the description adds what those annotations cannot: the delayed-vs-immediate effect depending on revision state, the SKILL.md deletion prohibition, and the read-only nature of historic revisions. This is real behavioral context beyond the structured hints.

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 compact sentences, front-loaded with the action, followed by the state-dependent effects and constraints. No filler and nothing repeated from the schema.

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 two-param tool with no output schema, the description covers effect timing, protected files, and immutable-revision handling. An agent has everything needed to decide and call correctly.

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% for both required params (path with example, skill_revision_id with format), so the schema carries the load. The description adds no syntax or format detail for either parameter, making 3 the correct baseline.

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 precise verb+resource ('Delete a file from a skill revision'), which cleanly separates it from deleteSkillRevision, deleteSkill, and deleteFile. The draft-vs-active distinction further pins down exactly what object is being mutated.

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?

Explains the consequences that determine when this is the right call: deleting from a draft is deferred until promotion, deleting from active takes effect immediately. It also states the read-only constraint on historic revisions and the workaround (create a draft). No alternative tool is named explicitly, so it falls just short of a 5.

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