gmail_empty

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

With no annotations, the description carries the burden and does well: it declares permanence ('permanently deleted'), states the confirm gate, and even discloses the return value ('count' of what Gmail said it would delete). It doesn't mention irreversibility/undo availability, permission requirements, or failure behavior, so it isn't fully complete.

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 short sentences with the destructive scope front-loaded, then the return value, then the confirm gate — a sound ordering with almost no waste. The parenthetical on confirm mildly repeats the schema description.

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 two-parameter destructive tool with no output schema and no annotations, the description covers what gets destroyed, that it is permanent, the safety gate, and the return value. Only minor gaps remain (error/undo semantics).

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 100% and both parameters (folder enum, confirm boolean) are documented in the schema, so the baseline applies. The description reinforces the confirm requirement but adds no new syntax or semantics beyond the schema's own 'outward-facing or destructive' wording.

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 (empty) plus the exact resource (Trash or Spam folder) and the scope ('EVERY conversation in it'), which cleanly separates it from siblings like gmail_trash or gmail_delete_forever that act on individual messages. An agent can pick this out without opening the schema.

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 makes the use case clear (bulk purge of a whole folder) and gates it behind confirm=true, which is the right conditioning for a destructive bulk operation. It does not explicitly name alternatives or state when not to use it (e.g., 'to remove a single message, use gmail_trash'), so it falls short of a 5.

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