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

Annotations already declare this is a non-read-only, non-destructive, closed-world mutation. The description adds meaningful side-effect context that annotations cannot convey: removing a tagger-supplied tag hides the file, expiry causes an export-time prompt, and followLatest migrates projects to newer versions automatically. Gaps remain on permission requirements, bulk semantics (up to 200 assetIds in one call), and partial-failure behavior, so this sits at the minimum-viable-plus level rather than fully covering a mutation.

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 core action, then organized by operation in the order an agent would care about them, ending with the useful exclusion ('Never renames anything'). It is a single dense sentence with several parentheticals, which keeps it short but makes individual semantics slightly harder to scan.

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 mutation tool with no output schema and only partial schema descriptions, the definition covers the semantics of every operation well, so an agent can pick the right arguments. It stops short of describing what the call returns, how bulk assetIds behave, or whether the operation is atomic, which an agent needs for confidence in a write tool.

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 only 33% (only licence and expiresAt are documented in the schema), so the description has to carry weight and largely does: it explains what addTags/removeTags do and the hidden-tag consequence of removal, what the licence note means (creator and usage terms), what expiresAt means operationally (last day usable, with export prompt), and the purpose of followLatest. The assetIds parameter is addressed only indirectly through the list_media provenance note, and the bulk (maxItems 200) nature of it is not explained.

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 (change) and resource (files of the library), then enumerates exactly which fields can be changed: tags, licence note, expiry date, followLatest. It also closes off a likely confusion with a negative scope statement ('Never renames anything'), which lets an agent separate it from rename/replace-style siblings without opening a 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?

It gives concrete provenance guidance for the required assetIds ('assetId from list_media from: folder or workspace') and situational guidance for individual operations ('good for logos' for followLatest, expiry effect on export). It does not explicitly name an alternative tool for cases like replacing a file or renaming, so the when-not path is only implied.

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