remove_incomplete_uploads

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

No annotations are provided, so the description carries the full burden. It discloses the destructive nature ('no undo', 'parts themselves are unrecoverable once aborted'), the [risk=medium] marker, the age-based protection, and what priorState records. It doesn't mention authentication/permission requirements, but the core behavioral risks are fully disclosed.

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 compact and front-loaded with a bold imperative line, then a concise behavioral warning, then a clean Args section. No wasted prose. Slightly longer than strictly necessary due to the priorState detail, but that adds genuine value for a destructive 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 destructive mutation tool with no annotations and no output schema, the description covers the essential risk profile, parameters, safety guardrails, and state side-effects. Could add permission requirements, but for a 4-param tool with 0% schema coverage this is a strong, near-complete package.

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 must carry all parameter meaning. It does: bucket_name (from bucket_ls), older_than_days (0=all), dry_run (preview without aborting), and target (MinIO config target, omit for default). Each of the 4 params gets meaningful explanation beyond raw names.

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 uses a specific verb+resource ('Abort abandoned multipart uploads (reclaims their parts)') and clearly scopes what it does. It distinguishes from the read-only sibling `incomplete_uploads_ls` by framing this as the destructive write counterpart. It doesn't name a sibling explicitly, so not a full 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 explicitly states the age guardrail ('Only uploads at least older_than_days old are touched (default 7), protecting in-flight uploads') and provides a dry_run preview path ('preview the matching uploads without aborting'). It's clear when to use it and how to safely preview before committing.

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