Delete old captures

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

Annotations already declare destructiveHint=true, and the description goes well beyond that: it explains the `keep` parameter is required to prevent accidental deletion, that `keep=0` removes all captures, that only files matching this mod's capture pattern are touched, that each file is re-checked for containment, that the whole set is validated before any unlink (so a refusal costs nothing), and that newest is determined by MTIME not filename index. This is rich behavioral disclosure that adds significant value beyond the 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 well-structured and front-loaded with the core action. It uses paragraphs to explain rationale, safety, and edge cases. It is somewhat long, but every sentence earns its place by explaining a non-obvious behavior or safety property. The only minor deduction is that some rationale could be tightened without losing meaning.

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 destructive tool with one required parameter, the description covers everything an agent needs: what gets deleted, how the keep count works, what happens with keep=0, the containment check, the validation-before-delete behavior, and the MTIME ordering. The output schema exists, so return values need not be described. This is complete.

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%, so the description carries the full burden. It explains `keep` in detail: it is required, deliberately has no default, `keep=0` is a real request that removes all captures, and it is compared against MTIME to decide which captures survive. This fully compensates for the schema's lack of description.

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 opens with a specific verb and resource: 'Delete all but the newest `keep` captures, and say which went.' It clearly distinguishes this from siblings like `shot` (which creates captures) and `read_capture` (which reads them). The purpose is unambiguous and immediately actionable.

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 explicitly explains when to use this tool: when captures have accumulated and need pruning. It contrasts with `shot` (which writes captures) and `read_capture` (which reads them), and explains the containment rule is the same as `read_capture`. It also warns against accidental destructive calls, making the usage context very clear.

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