cleanup apply

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

Annotations only indicate non-read-only and non-destructive, so the description carries the full burden. It discloses atomicity, the refusal condition, idempotency ('replay performs no additional actions'), output (per-row statuses and restore_id), and auth/cost. This is rich behavioral context beyond annotations.

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?

The description is extremely concise—one sentence with semicolons—yet packs the action, requirements, conditions, output, idempotency, and cost. It is front-loaded with the primary verb and resource, and every clause earns its place.

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?

The description covers the action, required inputs, behavior, output (including restore_id), idempotency, and auth/cost. It does not explicitly link to cleanup_preview or restore_cleanup, but the presence of a restore_id and the requirement of a preview_id imply the workflow. Given the output schema exists, return details are sufficient.

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 only 25% (idempotency_key's alias). The description lists the three required params and hints at candidate_hash's role via 'exact reviewed preview' and 'Refuses changed sources', but does not explain the format or exact meaning of each. It adds some semantics but not enough to fully compensate for the low schema 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 clearly states a specific verb ('archive') and resource ('exact reviewed preview'), and explicitly requires preview_id, candidate_hash, and request_id, which distinguishes it from cleanup_preview (which creates the preview) and other apply-like siblings. The 'Refuses changed sources' clause adds a distinctive behavior.

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 provides clear usage context: it is the apply step after a preview exists, requires those three parameters, refuses changed sources, and notes that replay is idempotent. It implies when to use it but does not explicitly name alternative tools or state 'use after cleanup_preview'.

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