incomplete_uploads_ls

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

No annotations are provided, so the description carries the disclosure burden. The '[READ]' tag and the return-envelope format description add behavioral transparency, and the 'initiated time null' caveat about data provenance is useful. However, it doesn't disclose pagination cursor behavior, rate limits, or whether results are ordered/deterministic.

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?

Compact and front-loaded with the [READ] tag and purpose in the first line, followed by a return-format explanation and per-arg documentation. The args section is organized and readable. Slightly verbose in the return-format section but no wasteful content.

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?

The tool has no output schema, so explaining the return envelope ('truncated', 'returned', 'limit') in the description is valuable. The per-argument documentation covers the 4 params at 0% schema coverage. The truncation-re-run guidance handles the edge case well. Could benefit from noting expected sort order or how it relates to object_ls, but it's fairly complete for a listing tool.

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 there are 4 parameters, so the description must compensate. It does explain each parameter inline (bucket_name from bucket_ls, prefix for key filtering, limit for max uploads, target as MinIO target name from config). This fully covers all 4 parameters' semantics and even adds defaults, though the default values already exist in the schema.

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?

Clear verb+resource: lists in-flight/abandoned multipart uploads. The '[READ]' prefix signals non-mutating behavior, and the description distinguishes this from sibling tools like remove_incomplete_uploads (which mutates). The title/name align perfectly with the described purpose.

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 explains the truncation envelope and instructs re-running with a higher limit when truncated=true. It references bucket_name 'from bucket_ls' as a source for the argument, providing linkage to sibling tools. However, it doesn't explicitly contrast with remove_incomplete_uploads or object_ls when deciding which to call.

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