compute.plan_storage_cleanup

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

Annotations already declare readOnlyHint=true, and the description reinforces that with 'No files deleted', which is consistent but somewhat redundant. It does add value by saying the result reports 'paths and blockers' and that the actual deletion happens separately with confirmation, but it omits scope details such as whether the plan is persisted or how long it stays valid.

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?

Two tight sentences with zero filler; the read-only guarantee and the review-before-apply workflow are front-loaded in that order.

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?

Because there is no output schema, the description usefully states what comes back (paths and blockers) and how the plan is consumed. It falls short only on the six undocumented input parameters, which are non-trivial for a scoped storage operation.

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 six parameters, so the description carries the full burden, yet it only implicitly maps the four cleanup categories to the kind enum. It says nothing about node_id, project_id, root_id, source_node_id, or run_id, so an agent can't tell which node/root scope or which run an optional filter applies to.

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 ('Plan exact-file cleanup') plus the resource and enumerates the four categories (stale-code, disposable, replica, cache) that map to the kind enum. It differentiates from the apply step by noting cleanup is applied 'separately' after review, though it doesn't name compute_apply_storage_plan or compute_scan_storage explicitly.

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?

Clear on context: use this to preview paths and blockers before a separate apply with confirmation. The plan-then-apply sequencing is stated, which is the key usage decision, but no explicit sibling alternatives or exclusions (e.g., vs compute_scan_storage or compute_report_storage) are given.

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