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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds material facts annotations cannot: no object appears at the key until completion, parts are billed until then, and an upload must be explicitly aborted to stop the charges. That is exactly the lifecycle risk an agent needs before invoking.

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 the core action and the trigger condition, and every sentence carries information. The final workflow sentence is a compressed, dash-heavy telegraph ('Then: presign_upload_parts for URLs, PUT each part yourself keeping the ETag each returns...') that costs a little readability for its density.

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?

No output schema exists, yet the description names the return value (uploadId) and closes the loop on the full workflow and cleanup path. For a 6-parameter mutation with nested metadata, nothing an agent needs to call it correctly is missing.

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 100%, so key, bucket, overwrite, contentType, userMetadata and connectionId are already documented (including overwrite's dual check at start and completion). The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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+resource ('Opens a multipart upload') and immediately demarcates the case it exists for: a file too big for a single PUT, with the 5 GiB S3 limit as concrete grounding. An agent can distinguish this from write_object without reading either schema.

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?

Explicitly gives the when ('file too big for one PUT'), names the sibling tools to use afterwards (presign_upload_parts, complete_multipart_upload) and the escape hatch (abort_multipart_upload if you give up). No inference required to pick or sequence the tool.

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