remove_incomplete_uploads

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

Goes well beyond the destructiveHint=true annotation by disclosing that the parts are unrecoverable, that there is no undo, that priorState records only a count and sample, and that the age threshold shields in-flight uploads. These are exactly the operational facts an agent needs before a destructive call.

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?

Front-loaded with risk classification, then one tight behavioral paragraph, then a compact args block. Nothing is padded; the args repetition is justified because the schema carries no descriptions.

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, non-idempotent tool with no output schema, the description covers safety profile, irreversibility, guardrails, and every parameter. There is no output schema to explain and return behavior (priorState summary) is already noted inline.

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 the burden and it does: all four params are documented with meaning beyond the schema, including '0 = all' for older_than_days, the preview semantics of dry_run, and the config-derived target. It also cross-references bucket_ls as the source of bucket 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?

States a specific verb and resource ('Abort abandoned multipart uploads') plus the effect ('reclaims their parts'), which clearly separates it from siblings like incomplete_uploads_ls (which only lists). The '[WRITE][risk=medium]' prefix front-loads the operation class.

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?

Gives clear conditions for use: only uploads at least older_than_days old are aborted, protecting in-flight uploads, and dry_run previews matches. It stops short of explicitly naming a companion tool (incomplete_uploads_ls) as the pre-check alternative, so it is clear context rather than full when/when-not guidance.

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