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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description goes well beyond them: it enumerates what is deleted, what is always preserved (newest image per repository, images pulled in the last 7 days), the delayed space reclamation at weekly GC (Sunday 03:00 UTC), and the credentials.write requirement. This is exactly the extra context that annotations cannot carry.

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 dense sentences with the trigger condition front-loaded and no filler. The closing instruction about what to tell the user ('say that instead of promising room now') is useful but slightly meta and adds length; otherwise it is tight.

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 no-arg, destructive, non-idempotent operation with no output schema, the description covers action, scope, preserved data, side-effect timing, prerequisite tool, and auth scope. Nothing an agent needs in order to call it and report it correctly is missing.

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?

The tool takes zero parameters, so there is no parameter semantics to add and the baseline is 4. The description correctly does not invent any inputs.

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 (start ... retention now), the exact resource (the organisation's image registry retention), and the scope (every registry project), plus what actually happens as a result (images the retention policy does not keep are deleted). It is clearly distinguishable from the sibling set_registry_retention, which it explicitly references.

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?

Gives an explicit trigger condition ('after set_registry_retention when the registry is full and a push is blocked') and names the related sibling tool. The agent knows both when to reach for this tool and which tool must precede it.

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