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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds genuinely useful behavior beyond that: it is a partial update (only passed fields change), it does NOT release the version, it mutates shared product structure (a consent/caution signal), and it returns the version. It does not explain permissions or error behavior, but the added context is substantial.

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 what changes and what does not, then the caution and return value. Every sentence carries information; the middle caution clause is slightly dense but earns its place.

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 6-param mutation with one required field, full schema coverage, and annotations covering safety, the description supplies the remaining essentials: partial-update scope, non-release behavior, shared-structure side effect, and the return value (compensating for the absent output schema). Nothing critical 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 build/major/minor/notes/designFileUrl semantics (including the full-replacement behavior of notes and the null meaning of designFileUrl) are already documented in the schema. The description only restates the affected field set, adding no syntax or constraint beyond what the schema supplies — the baseline 3.

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 (changes) and resource (a version's number, notes, design file) and immediately scopes it with 'only the passed fields' and 'does not release it', which cleanly separates it from version_release and version_create. An agent can identify the operation without opening the 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?

Provides a real usage condition — only perform this at the user's request or with their consent because it changes shared product structure — and implicitly routes release operations elsewhere via 'does not release it'. It stops short of explicitly naming alternative tools for adjacent cases (e.g. version_release), so it is clear context rather than exhaustive 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.