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 does so: it discloses the save-to-disk side effect, inline return for text-like types, the maxSizeMB refusal, the never-overwrite guarantee, and an explicit prompt-injection security boundary. This is unusually complete behavioral disclosure for a mutation-with-side-effects tool.

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 with the core action and the user-consent gate, followed by return behavior, defaults, and safety limits. Every sentence adds operational value; the security-boundary block is long but justified for an untrusted-content tool.

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 no output schema, the description explains return values (file paths plus inline text for text-like types) and how to read other files. Combined with the safety and default-behavior notes, nothing an agent needs to invoke this 7-param tool 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?

Schema coverage is 86%, so the baseline is 3, but the description adds meaning beyond the schema: it explains that indexes/filenames come from get_message, that omitting them downloads everything, and that maxSizeMB is a hard refusal threshold. It does not detail dir/folder/account defaults beyond what the schema already states.

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 (Download) and resource (attachments of one message), and scopes it to a single message via the uid. It is clearly distinguished from siblings like get_message (metadata) and search_messages.

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?

Explicitly gates use on user agreement, explains the default case (all attachments unless indexes/filenames given), points to get_message as the source of those selectors, and tells the agent to read non-inline files from the returned path. Conditions for the alternative paths are spelled out.

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