delete_sandbox_image_version

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

Annotations already flag destructiveHint=true, so the bar is lower. The description goes beyond that with real consequences: an index takes its platform manifests with it, and the space is reclaimed at the weekly garbage collection. It does not say auth/permission requirements or what the response looks like.

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?

Four compact units: purpose, encoding rule, deletion consequence, and route. Front-loaded with the purpose. The route line is slightly redundant with the opening sentence but still reinforces the operation.

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 3-param destructive action with no output schema, the description covers purpose, encoding, cascade behavior, and GC timing. Missing explicit auth requirements keeps it just below full completeness.

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 coverage is 0%, so the description must compensate. It explains that app must be URL-encoded when it contains slashes (team%2Fapi for <sandbox>/team/api), which is genuinely useful. However, name and digest are left without any format/semantic explanation.

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?

Specific verb (Delete) + resource (a version of one of the sandbox's images in the p7y registry), with the exact HTTP route. It is unmistakably distinct from siblings like list_sandbox_images or delete_sandbox_file.

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 the name and the URL path, but the description never states when to use this versus alternatives or preconditions. It does add the practical note that URL-encoding is needed for names containing slashes, which is indirect usage guidance.

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