delete_submission_files

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds context that the submission must be 'editable' and that confirmation is required, which aligns with the confirmation_token parameter. However, it doesn't disclose irreversibility (beyond destructive), side effects, or what constitutes 'editable' – leaving the agent to infer these. It adds some value beyond annotations but not rich detail.

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 a single concise sentence with no fluff. However, it's so brief that it sacrifices necessary detail, veering toward under-specification rather than efficiency. Still, it front-loads the core action and condition effectively.

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 3 parameters, no output schema, and no annotation beyond destructiveHint, the description is severely incomplete. It lacks parameter semantics, usage conditions (e.g., must be editable, need confirmation token), what happens on success/failure, and any relation to the preview workflow. An agent would be guessing on critical aspects.

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%, and the description provides no explanation of assignment_id, course_module_id, or confirmation_token. It only hints at 'confirmación' mapping to the token, but doesn't clarify the IDs or their roles. With zero coverage and no compensation from the description, parameter semantics are essentially absent.

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 the action ('Elimina todos los archivos' = deletes all files) and the resource ('de una entrega' = of a submission), adding a condition ('editable tras confirmación' = editable after confirmation). It distinguishes from siblings like preview_delete_submission_files and remove_submission by focusing on file deletion, but doesn't explicitly mention it's the confirm counterpart to the preview, so not a perfect 5.

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 no guidance on when to use this tool versus alternatives. Sibling tools like preview_delete_submission_files and remove_submission are not mentioned, and there's no indication of prerequisites (e.g., submission must be editable, preview first). The bare requirement 'tras confirmación' hints at a workflow but doesn't explicitly say to use the preview first.

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