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

Annotations only mark it non-read-only and non-destructive; the description adds material behavior: max upload sizes, two-phase URL upload, attachment multiplicity, and a hard limitation that files cannot be deleted through MCP. No contradiction with annotations.

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 purpose and dense but purposeful sentences; every clause (token destinations, size limits, upload modes, deletion limitation) carries operational weight.

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 two-mode upload tool with no output schema, the description supplies the key attachment identifiers and uploadURL flow. It falls short by not naming file_upload_complete as the completion step and by not fully specifying the return shape.

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 100% for both parameters, and the schema already states the base64 size limit and the URL-upload alternative. The description reinforces the workflow but adds little parameter-level meaning beyond 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?

States a specific verb and resource, then immediately distinguishes the two attachment identifiers (attachToken vs fid) and the two upload modes. An agent can tell this is the upload primitive rather than file_upload_complete or file_get, though the sibling is not named.

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?

Explains the dataBase64 path for small files and the uploadURL PUT path for larger files, including size limits. However it does not explicitly name file_upload_complete as the final step or provide conditions for choosing among sibling file tools.

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