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

Annotations already declare readOnly=false, destructive=false and idempotent=true, and the description is consistent with that, adding real context on what exactly gets invalidated and that the effect is scoped to the site's own domain. It does not cover permissions/auth or whether purging is immediate or async, which keeps it below a 5.

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 sentences, no filler, with the affected cache scope front-loaded and the disambiguation pointer placed at the end where it's most actionable. Every clause carries information.

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 2-parameter cache-purge with no output schema and annotations already covering the safety profile, the description covers scope, targeting and alternatives well. The remaining gap is the identifier-selection rule (required vs optional, precedence), which the schema leaves at default null for both.

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 0%, so the description must carry the parameter burden; it does say the two parameters are alternative identifiers, which is useful. But it doesn't state whether one is required, which one wins if both are supplied, or what the UUID format is — roughly half of the needed semantics remain undocumented.

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 precise verb and target: delete the nginx proxy cache of a website's slug-less paths, enumerating the affected paths (index, contacts, llm, sitemap, AMP included). It explicitly carves out the sibling case (article/page/collection paths go to purge_cache_group), so an agent can distinguish it from purge_cache_group, purge_nginx_cache and clear_*_cache siblings without opening schemas.

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 both the when (slug-less site paths on the site's own domain) and the when-not (article/page/collection paths -> purge_cache_group with slugs). It also states the invocation rule 'Pass website_id or website_uuid', leaving no routing inference to the agent.

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