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

Annotations already establish idempotentHint=true and destructiveHint=false. The description adds real value beyond them: which caches are touched, that the nginx purge only applies once published, and the specific error code raised for slug-less advertisements.

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?

Two compact sentences, the cache targets front-loaded and the parameter/error detail following. Dense but every clause carries information; 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 cache-invalidation tool with no output schema, the description covers targets, triggering conditions, and the error case. It omits what a successful response looks like and whether elevated permissions are needed, minor gaps given annotation coverage.

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% and neither parameter has a schema description, but the description compensates by telling the caller the two are alternatives ('Pass advertisement_id or advertisement_uuid'). It does not address what happens if both or neither are supplied, which matters since required parameters count is zero.

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 (clear), resource (advertisement cache), and scope (every website it runs on), plus the exact cache layers affected: Redis slave list cache and nginx proxy cache of /s/<slug>. This is clearly distinguishable from purging a website-wide nginx cache or a page cache.

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 concrete invocation guidance ('Pass advertisement_id or advertisement_uuid') and a failure condition (ERR_ADVERTISEMENT_NO_SLUG when the advertisement has no slug). It does not explicitly name purge_website_cache_all or clear_page_cache as fallbacks, so sibling routing is implied rather than stated.

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