drive_save_attachment

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

With zero annotations, the description carries the full burden, and it delivers: discloses the streaming mechanism (Gmail→Drive direct, never through local disk), the non-overwrite collision behavior, that nothing is returned in the result, and that it is non-destructive and narrowly scoped to existing Gmail attachments. This is unusually rich behavioral disclosure for a tool with no annotation safety net.

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 dense sentences, each earning its place: the core action with mechanism, the collision/refusal behavior, and the capability exclusions. Information is front-loaded — the action and key constraint appear in the first sentence — and there is no filler, no restatement of the tool name, and no repetition of schema content.

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 mutation tool with no annotations and no output schema, the description covers the essentials: what it writes, where, what it will not overwrite, what it returns (nothing in the result), and what it cannot do. Minor gaps remain — the shape of the success/error result and Drive permission requirements — but nothing an agent needs to avoid a destructive or wrong call 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 100%, so the schema already documents all five parameters clearly — including the name default ('Defaults to the attachment's own (sanitised) filename') and the cross-reference in attachmentId ('from gmail_read_message'). The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 states a specific action ('Save a Gmail attachment straight into a Google Drive folder') with a clear resource and scope. It behaviorally distinguishes itself from siblings like gmail_get_attachment by noting the bytes 'never come back in the tool result' and from a hypothetical upload tool by insisting it 'cannot upload a local file.'

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 preconditions ('only an attachment already on a Gmail message') and explicit exclusions ('cannot delete anything, cannot upload a local file'), so an agent knows what not to attempt. However, it never names an alternative tool or states 'use X instead when...' — sibling routing is left to inference, which is a gap for a tool sitting between gmail_* and drive_* families.

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