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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds meaningful behavioral context beyond that: it fetches the page live now, lists cache layers in purge order (innermost first), and verifies whether a purge clears the finding and keeps it cleared. It does not explicitly state that no purge is actually performed, which the annotations imply but the text leaves slightly ambiguous.

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?

It is a single run-on sentence that front-loads the finding name but then reads as an undifferentiated dump of plan contents. It is information-dense with little waste, yet the lack of sentence breaks or grouping makes it harder to parse than it needs to be.

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?

With no output schema, the description carries the burden of describing what the tool returns, and it does so thoroughly: homepage fetch, Age, cache layers in purge order, declared HTML lifetime, fresh-read comparison, and purge-clearance verification. An agent knows what to expect back, though the ambiguity about whether a purge is executed is a minor gap.

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 50%: the 'id' parameter is documented as a report id that still triggers a live fetch, while 'domain' is undocumented. The description reinforces that state is fetched live but adds no format, syntax, or meaning for either parameter beyond what the schema already provides. Baseline 3 for partial coverage.

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 names a specific resource ('A fix plan for STALE_CACHE_SERVED') and enumerates the artifacts it produces, distinguishing it from the other fix_* siblings that each target different findings. It is a noun phrase rather than a clean verb+resource, but 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?

Usage is implied by tying the tool to the STALE_CACHE_SERVED finding, so an agent can infer this is the remedy for that finding. However, there is no explicit when-to-use/when-not statement, no alternative named, and no guidance on how it relates to sibling fix_* tools or explain_finding.

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