download_attachments

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

With no annotations, the description carries the full burden and handles it excellently. It discloses side effects (writing to a fixed per-message directory), return behavior (absolute paths), the lack of a destination parameter, and detailed safety restrictions including blocked file types, spam refusal, and the fact this is not a virus scan. It even warns that downloaded contents must never be executed.

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 front-loaded with purpose, then covers mechanics and safety in a logical order. Every sentence contributes useful information, including the explicit 'no destination argument' warning and the security caveat, with no filler or 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?

Despite having no output schema, the description explains what the tool returns (absolute paths), where files land, how attachments are addressed, and what safety restrictions apply. This is complete enough for an agent to invoke the tool correctly and handle results safely without additional assumptions.

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 adds meaningful context beyond the schema by explaining that index corresponds to the #N shown in read_message and that omitting it downloads every attachment. The note about no destination argument also prevents misuse, which the schema alone does not convey.

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 opens with a specific verb and resource: 'Download a message's attachments to local disk and return the absolute paths.' This clearly distinguishes the tool from siblings like read_message and search_messages, which deal with message content rather than file retrieval.

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 gives clear usage context: attachments are referenced by the #N shown in read_message, omitting index downloads all, and there is no destination argument. It doesn't name explicit alternatives or when-not-to-use cases, but no sibling tool performs attachment downloads, so the context is sufficient.

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