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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=false, so the mutation/idempotency profile is covered; the description adds real context by disclosing that AMP variants are also purged and that slugs are conditionally required. It does not explain permissions, whether the purge is immediate/propagated, or what happens if slugs are omitted for a slug group. Note: destructiveHint=false alongside 'Delete the cache entries' is defensible for recoverable cache, so this is not scored as a contradiction.

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 tight sentences with the core action front-loaded, followed by the conditional slug rule and a concrete example. Little waste, though the example partially duplicates the slug-requirement sentence and the final pointer names a non-existent tool.

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 3-parameter mutation tool with no output schema and no parameter descriptions, the description covers the input side adequately but leaves gaps: no statement of what a successful purge returns or how to verify it, no guidance for the non-slug group case, and a dangling prerequisite reference to get_nginx_cache_targets.

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 load — and it largely does: it names the group values that require slugs (pages, articles, collections, advertisements, leads) and gives a concrete example (host='pt.neeblo.com', group='articles', slugs=['sample-article']) that shows the host format. 'host' itself is still only demonstrated, not explained, and non-slug group values are unenumerated.

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 and resource: 'Delete the cache entries of a group (including AMP variants).' The AMP-variant detail distinguishes it from a plain page/article cache clear, but it never names the closely related siblings (clear_page_cache, clear_article_cache, purge_website_cache_all, purge_nginx_cache) so an agent must infer the boundary.

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?

Adds a useful prerequisite ('Check the group first with get_nginx_cache_targets') and states that slugs are required for slug groups, enumerating which groups those are. However, the referenced target tool name does not exist in the sibling list (the nearest sibling is get_cache_targets), and there is no guidance on when to use this versus clear_page_cache / clear_article_cache / purge_website_cache_all.

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