upload_attachment

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

With no annotations provided, the description carries the burden of behavioral disclosure. It communicates that this is a write operation ('upload', 'Scope: attachment:write') and explains the output contract (an attachment ID). It doesn't mention limits such as file size or cleanup, but the core behavior of creating an attachable artifact for send_mail is clearly disclosed.

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?

Two short sentences carry the operation, the return value, the downstream consumer, and the required scope. There is no filler, and all essential information is front-loaded.

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 one-parameter tool with no output schema, the description covers what the tool does, why to call it, what it returns, and the required scope. It could optionally mention failure conditions or size/type restrictions, but nothing needed for invoking 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?

The schema already describes file_path as 'Absolute path of the local file to upload' with 100% coverage. The description repeats the concept of a 'local file' but adds no format, size, or path-resolution details beyond the schema, so it doesn't meaningfully raise the baseline.

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 uses a specific verb ('Upload') with a clear resource ('a local file as a mail attachment') and states the key result: an attachment ID for send_mail. This distinct role is enough to separate it from all sibling mail operations, even without an alternative upload tool.

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 explicitly says the returned attachment ID is for send_mail, which tells an agent when to call this tool: before sending a mail that needs an attachment. It doesn't explicitly list exclusions, but there are no competing upload alternatives in the sibling set to disambiguate against, so this guidance is sufficient.

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