Upload Attachment

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

Annotations already declare the write/open-world/non-idempotent profile, so the lower bar applies; the description adds the genuinely useful behavioral constraint that inline content is capped at 32 KiB decoded and discouraged entirely. It does not mention upload lifetime, expiry, or what happens if the upload is never consumed by a send, which would round out the mutation picture.

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?

Three short sentences, front-loaded with the routing decision and then the constraint, with zero redundant restatement of the tool name or schema fields.

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 an output schema present, return values need no explanation, and the description covers the routing and size-limit decisions an agent must make before calling. The one gap is what to do with the resulting upload reference when composing the subsequent send, which the agent must infer.

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%, so the baseline is 3; the description earns an increment by steering parameter choice rather than just restating it, telling the agent to avoid content_base64 for real files and use a different presigned-upload path instead. filename, content_type, and idempotency_key get no added meaning, but their schema entries are already complete.

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?

The description establishes that this tool prepares an attachment for the Sending API and explicitly names the sibling it is not for real files (sending_create_attachment_upload). What it actually produces (an upload record to reference later) is only implied by 'Use this before sending,' so it falls just short of a crisp verb+resource statement.

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?

It gives explicit when-to-use (before sending an attachment), a named alternative with the condition that selects it (real files → sending_create_attachment_upload with an out-of-band PUT), and a bounded fallback (inline base64 only for tiny agent-authored files, 32 KiB decoded). Nothing is left to inference.

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