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

Annotations only declare the generic write/non-destructive profile; the description adds real behavioral context beyond that: every version is retained and restorable by an owner, a library-derived skill forks into a workspace copy on first change, and the reply carries a file the agent must write over its installed copy. These are the traits an agent cannot infer from readOnlyHint=false or destructiveHint=false.

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?

Front-loaded with the purpose and trigger before the caveats, and nearly every sentence carries required information (access gate, versioning, the body's exclusion list, the file-write side effect). It is a dense single paragraph, but the density is load-bearing rather than filler.

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 five-parameter mutation tool with no output schema, the description covers the access prerequisite, version retention, the fork-from-library behavior, the content boundaries of the body field, and what the response contains. Nothing an agent needs before calling it 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 coverage is 100%, so the baseline is 3, but the description adds genuine semantics: 'body' is the instructions only and must exclude the SKILL.md front matter, Inputs list and Changing-this-skill section, and 'reason' is a one-line history entry. That goes beyond the schema's own wording for these fields.

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 and resource ('Save a new version of one of this workspace's skills') plus scope ('every agent in the workspace follows the change from its next use'). It is clearly distinguishable from siblings get_skill and list_skills, which read rather than version a skill.

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?

Gives an explicit trigger ('Call it when the person asks you to change how a skill works') and a hard precondition ('Allowed only where list_skills shows access: edit'). It also distinguishes itself from add/list tools by naming the sibling that gates it.

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