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

destructiveHint=true is already declared, but the description adds the crucial nuance that 'Nothing is lost (the CDN refetches from the origin) but the origin takes the refill load' — explaining the real consequence of the operation and warning about origin load that annotations alone cannot convey. The 'WRITE.' prefix also signals the side-effect class.

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, front-loaded with the operation class and the core action, followed by the impact note and the API endpoint. No filler text.

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 two-parameter mutation with no output schema, the description covers the action, the scope options, the safety consequence, and the origin-load side effect. An agent has everything needed to decide and invoke 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 description coverage is 100%, so both parameters are already documented in the schema. The description's 'everything, or only files carrying a cache tag' restates the cache_tag semantics rather than extending them, so the baseline 3 applies.

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?

The description states a specific verb and resource ('Purge the cached content of one pull zone') and narrows the scope to a single pull zone, which distinguishes it from the broader bunny_purge_url sibling. The two granularity modes (everything vs. cache-tagged files) are named up front, so the purpose is unambiguous.

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?

The description conveys the two operating modes (full purge vs. tag-scoped purge), which implies how to invoke it, but it never says when to choose this over bunny_purge_url or any other sibling, nor are there prerequisites or exclusions. Usage is inferable but not stated.

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