Skip to main content
Glama

Purge Cloudflare zone cache

cloudflare_zone_cache_purge
Idempotent

Purge cached copies of specified URLs, hosts, prefixes, or tags in a Cloudflare zone, up to 100 per request, so subsequent requests fetch updated content from the origin.

Instructions

Purge cached copies of the given URLs, hosts, prefixes or tags in one zone, up to 100 at a time; nothing stored is deleted, the next requests fetch from the origin; for the whole cache use cloudflare_zone_cache_purge_all.

Input Schema

NameRequiredDescriptionDefault
tagsNo1–100 cache tags to purge from the cache.
urlsNo1–100 URLs to purge from the cache.
zoneYesThe zone domain or 32-hex id.
hostsNo1–100 host names to purge from the cache.
accountNoThe label of the credential pair to use, or "default" for the unlabeled one; left out, the unlabeled pair, else the only label.
prefixesNo1–100 prefixes (host/path…) to purge from the cache.

Output Schema

NameRequiredDescriptionDefault
zoneYesThe zone whose cache was purged.
labelYesThe account label.
purgedYes
purge_idYesThe Cloudflare purge identifier, if returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Adds value beyond the annotations by explaining that nothing stored is deleted and that subsequent requests refetch from the origin, which contextualizes destructiveHint=false and idempotentHint=true. However it adds no information about rate limits, per-type constraints, or whether purges propagate asynchronously — behavior the agent would need on a real mutation call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with scope first, semantics second, and the alternative last; nothing is wasted. It is packed with clauses but remains readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With full schema coverage, annotations, and an output schema, the description covers what is needed to pick the right tool and understand the batch limit and non-destructive effect. The remaining gap is mixing purge types and async propagation, which can matter for a cache-invalidation operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter (including the 1–100 limits and the credential label semantics) is already documented in the schema. The description only restates the 100-item ceiling and the four purge modes, adding no syntax or precedence guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Purge cached copies of the given URLs, hosts, prefixes or tags in one zone') and immediately scopes it to a single zone, which distinguishes it cleanly from cloudflare_zone_cache_purge_all and from the read/edit siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes whole-cache purges to cloudflare_zone_cache_purge_all, which is the main alternative an agent would confuse this with. It does not say whether the four purge types (urls/hosts/prefixes/tags) may be mixed in one call or must be sent separately, so one real selection question is left unanswered.

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