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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description adds the context the annotations cannot — two-week image TTL, which CDN layers are purged and the condition for Cloudflare inclusion, and which storage backends are out of scope. It omits what happens to paths that were never cached and whether any confirmation is returned.

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 tight sentences, front-loaded with the [write] marker and the verb. Every clause carries a distinct fact — scope, timing, exclusions, path format, account selector — with no 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 mutating tool with no output schema, the description covers trigger, coverage, cache lifetime, batching limit and account selection — enough to call it correctly. The remaining gaps (mandatory-ness of id vs uuid, return/confirmation behavior) are minor but real.

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 0%, so the description has to carry the parameter load, and it largely does: `paths` format with a concrete example ('images/logo.png') and a cap of 200 entries, plus the account selector `storages_account_id` / `storages_account_uuid`. It does not say whether one of the two account identifiers is mandatory or which wins if both are passed.

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 concrete verb+resource: clearing the CDN cache of files served by a Google Drive / OneDrive / Dropbox / Yandex Disk account, and names the layers (nginx, Cloudflare on cdn-<id>.<zone>). It implicitly separates itself from page/website cache siblings via the storage-account scope, but never names purge_nginx_cache, clear_page_cache, purge_website_cache_all or purge_cache_group, so the boundary must be inferred.

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?

"Use it after replacing or deleting a file: images are cached for two weeks" gives an explicit trigger and rationale. It also states exclusions ('Bunny, R2 and S3 files ... are not covered'), which prevents misfires, but it does not route the agent to a named alternative for those excluded cases.

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