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

Annotations only flag readOnlyHint=false; the description carries the rest, disclosing that the operation creates a per-user override, that the source version is recorded for provenance, and that deletion is a reversible path back to the published skill. It does not say what happens on a second fork of the same slug or whether the fork is user-scoped versus workspace-scoped.

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 short sentences, front-loaded with the core action and effect, then provenance, then lifecycle. Nothing is repeated from the schema and no sentence is 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 single-parameter mutation with no output schema, the description covers effect, provenance, and cleanup paths, which is most of what an agent needs. Still missing is failure behavior (forking an already-forked slug) and whether the returned copy is the same object the caller later edits.

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% and the schema already tells the agent the slug comes from skills_search, so the baseline is met. The description adds genuine meaning by stating the slug is preserved in the copy, which tells the caller the identifier has behavioral consequences beyond being a lookup key.

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 ('Copy a published skill into your own skills') and adds the essential semantic twist that the copy keeps the slug and therefore shadows the published version for the caller. That distinguishes it from skills_create, which would make a new skill rather than override an existing one.

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 clear downstream routing: edit the copy with skills_update, delete it with skills_delete to restore the published one, and take the slug from skills_search. It never explicitly contrasts with skills_create or states when forking is preferred over creating from scratch, so it stops short of full when/when-not guidance.

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