cutbolt_cache_prune

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

Annotations declare idempotentHint=true and openWorldHint=false, so the safety profile is partly covered. The description adds genuinely useful destruction scope: it states which entries are removed and, importantly, which artifacts are preserved. It does not cover auth requirements or what a prune reports back, so it falls short of a 5.

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?

One sentence, front-loaded with the action and budget constraint, closing with the non-destructive scope guarantee. No filler and no repetition of schema content.

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 only two parameters, full schema coverage, and no output schema, the description supplies what an agent needs to invoke it safely: what it evicts and what it leaves alone. Minor gaps remain around whether results over budget are still produced and what the call returns, though the schema hints at the former.

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 100% and the Policy object already documents max_bytes, max_entries, their ranges, and the LRU eviction rule. The description's 'explicit byte/count budgets' merely restates that, adding no format or default detail beyond the schema, so the baseline 3 applies.

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?

Names a specific verb (evict/prune) and resource (least-recently-used derived cache entries) bounded by explicit byte/count budgets. The clause 'source media and exported files are not removed' sharply delineates scope, distinguishing it from cache_inspect and from any media/file tool in the sibling list.

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 'evict ... to explicit byte/count budgets' – an agent can infer this is for reclaiming cache space – but there is no explicit when-to-use, no prerequisite, and no named alternative such as cutbolt_cache_inspect for checking usage first.

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