drive_empty_trash

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

With no annotations, the description carries the disclosure burden and does it well: it declares permanence, irreversibility, the confirm=true requirement, and the precise failure mode (invalid_argument with nothing deleted). It even explains that the Trash may hold items trashed by hand, which is why an unconditional empty must be explicit. Permission requirements and the success response are not covered.

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?

Short and front-loaded: the destructive outcome and its irreversibility come first, then the guard parameters, then confirm. The sentence justifying why unconditional emptying must be explicit is slightly explanatory but earns its place by motivating the guard.

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 3-parameter destructive tool with no annotations and no output schema, the definition covers what is destroyed, the safety guards, the confirm requirement, and the failure behavior. Only the success result (e.g. how many items were removed) and any permission prerequisites are left unstated.

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, but the description adds real value beyond the per-parameter text by spelling out the interaction between only_if_all_match and all, including that omitting both yields invalid_argument. That cross-parameter constraint is not visible in the schema.

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 (permanently delete) with an explicit scope (everything in the Trash), which distinguishes it from sibling single-item tools such as drive_delete_forever and from drive_trash (which only moves items to trash). The 'cannot be undone' qualifier reinforces the irreversible nature up front.

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 tells the agent that it must supply either only_if_all_match or all=true, and that the call otherwise fails with invalid_argument and touches nothing — that is actionable conditional guidance. It also explains why the unconditional path must be deliberate. It stops short of naming sibling alternatives like drive_delete_forever for single-item deletion.

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