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

Goes well past the annotations (which only declare readOnly/non-destructive/closed-world) by disclosing that parts are stored and billed until removed, that results are ordered by key rather than date, and that olderThanDays filters only the page the provider returned so a truncated answer can hide older uploads.

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-loads what the tool returns and why it matters, then layers the ordering and filtering caveats. Dense and semicolon-heavy, but each clause carries information; nothing is padding.

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?

With no output schema, the description still conveys ordering, the truncation signal, and the filtering pitfall, which is what an agent needs to interpret results. It stops short of describing the returned record shape apart from the uploadId.

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 already 100%, but the description adds genuine semantics beyond it: prefix is framed as the tool for escaping a truncated page, and olderThanDays is flagged as a post-hoc filter over the returned page, which the schema does not say.

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 the exact resource and scope: multipart uploads that were started and never finished, with their parts retained. It implicitly separates itself from list_objects (completed objects) and points at abort_multipart_upload by noting the uploadId is the only way to abort one.

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 ('where to look if an upload was interrupted or its id was lost') and guidance for narrowing with prefix when a page is truncated. It never names an alternative tool (e.g. abort_unfinished_uploads) as a when-to-use swap, so it stops short of the top band.

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