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

The annotations only declare the mutation profile; the description adds the behavior that actually matters: unlisted files carry over from the current version, expectedVersion guards against clobbering a concurrent publish, and the name is owned by a team or by the operator. It also discloses a content constraint (SKILL.md must carry YAML frontmatter with name and description) that governs whether the call will succeed at all.

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?

Four dense sentences, front-loaded with the verb and the change-set model before the version and ownership rules. Almost every clause earns its place, though the '{ path, text } for text, { path, base64 } for binary' sentence duplicates the schema's files description verbatim.

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 non-idempotent write whose annotations are generic, the description covers the mutation model, conflict handling, ownership scope, and file-content prerequisites; an output schema exists, so return values need not be explained. Nothing an agent needs to call it correctly 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 the baseline is 3; the description earns a point by adding a validation rule not present in the schema (SKILL.md frontmatter must declare name matching the name parameter) and by restating the create-vs-update meaning of expectedVersion in operational terms. The files/removals format is largely repeated from the schema, so it is not full compensation.

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 ('Publish a new version of a skill') and immediately defines the form of the write ('as a change set'), which separates it from skill_get/skill_list without needing the schema. The scope of the change set (adds/replaces, removals, carry-over) is spelled out in the same opening sentence.

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?

Explicitly routes the agent on the key decision: expectedVersion 0 to create versus the version you read to update, plus what happens on CONFLICT. It also gives the team/no-team scoping rule. It stops short of naming an alternative tool (e.g., skill_get for reading the current version) or stating when not to publish, so it is clear context rather than a full when/when-not guide.

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