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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety baseline is set. The description adds genuinely new behavior: the purge is irreversible but self-healing ('the cache fills again from the origin') and the per-request URL limit of 30. It stops short of noting the origin-load consequence of a full-zone purge or any auth/permission requirement.

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 tight sentences: scope first, then the usage trigger and reversibility note. No filler, no restatement of the title, everything front-loaded.

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, the description covers what is cleared, when to use it, the extent limit, and the post-purge behavior. Only minor gaps remain (whether confirmation/return output exists, any zone-permission caveat), which are not critical to invoking it correctly.

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 67% — urls and zone are documented, the boolean 'everything' is not. The description compensates by explaining the everything-vs-addresses dichotomy and surfacing the 30-URL cap, which appears nowhere in the schema. That is real added value above the baseline 3.

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 — clear Cloudflare's cache of a zone — and immediately enumerates the two scopes (everything, or given addresses up to 30). It is unmistakably distinct from sibling cf_* tools like cf_dns_* or cf_settings without needing to open any 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?

Explicitly gives the triggering situation: after deploying changes when a visitor still sees the old page or a wrong page is cached. It does not name a sibling alternative, but the line 'Nothing to undo' implicitly rules out reaching for cf_undo/rollback.

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