Save an attachment

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

The description discloses that files are EPHEMERAL by default and self-delete after the TTL, which is important behavioral context beyond the annotations' readOnlyHint and destructiveHint flags. This adds transparency about the tool's lifecycle behavior and potential surprise to users.

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?

The description is three concise sentences, front-loaded with the primary action, followed by the intended use and the critical ephemeral behavior. Every sentence adds value with no redundancy.

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 tool with 8 parameters and no output schema, the description covers the return value (path(s)) and a key behavioral caveat (self-deletion). It doesn't enumerate error scenarios, but the schema covers parameter-level details, making the description sufficient as an overview.

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 75%, so most parameters already have descriptions. The tool description doesn't re-explain parameters, and it also doesn't clarify the undocumented uid and include_inline fields; however, these are reasonably inferable from their names and context.

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 clearly states the tool writes attachment(s) to disk and returns the path(s), using a specific verb and resource. It also gives concrete use cases (images, scanned PDFs, anything not text-extractable) that distinguish it from siblings like read_attachment and view_attachment.

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 to use for images, scanned PDFs, or anything not text-extractable, giving a clear when-to-use signal. It does not name alternative tools but implies that text-extractable content is handled elsewhere, which is adequate guidance.

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