production.cleanup_artifacts

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

Beyond the destructiveHint=true annotation, the description discloses what is always protected (recovery points of uncertain operations, applied proposals, registered assets) and that Candidate Actions are reported but never deleted. That is genuinely useful safety context. It omits what happens to the artifacts actually removed (trash vs. hard delete) and any confirmation requirements.

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 scope front-loaded, which is good. The parenthetical enumeration of record fields adds bulk that largely duplicates the output schema rather than helping an agent choose parameters.

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 annotations covering the destructive profile and an output schema covering return values, the description is complete on safety and scope. It falls short on the filtering knobs an agent must set to target a cleanup safely, leaving keep_last/min_age_days/categories semantics entirely to undocumented schema defaults.

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 0% across 5 parameters, so the description carries the full burden and only partially delivers: it explains dry_run's effect and repeats its default. The four filtering/retention parameters (keep_last, categories, min_age_days, operation_id) get no explanation, and the parenthetical field list reads as output record fields rather than parameter meaning.

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 the resource precisely (workspace checkpoints/qa/operations/working copies) and frames the tool as a lifecycle inventory that surfaces cleanup candidates. It is clearly distinguishable from the create_/restore_checkpoint siblings, though the verb 'inventory' undersells that the tool also performs cleanup when dry_run=false.

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?

It states that dry_run defaults to true and that deletion only happens otherwise, which implies the safe-first probe-then-execute workflow. It does not say when to run this vs. restore_checkpoint or create_checkpoint, nor when retention rules should lead an agent to skip cleanup entirely.

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