drive_trash_files

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

With zero annotations, the description carries full behavioral weight and does so thoroughly: ordered processing, one result row per item, per-row refusal isolation with concrete refusal reasons, preview-only behavior without confirm: true, folder-specific confirmFolder requirement, 30-day restore window, and the explicit absence of a permanent-delete path. This goes far beyond a typical description.

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 with the core purpose front-loaded and every clause adding value (batch limits, ordering, refusal isolation, guards, retention). Slightly long, and the middle sentence partially repeats schema content, but the density is justified for a guarded mutation tool with no annotations.

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?

Inputs are fully specified by the schema, and the description thoroughly covers behavioral semantics and failure modes given that no output schema exists. The main gap is that result-row fields are only hinted at ('one result row per item' plus refusal reasons) rather than enumerated, which an agent would need to parse the response reliably.

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 the schema already documents confirm ('previews every row and changes nothing'), confirmFolder ('a folder row without it is refused'), and expectedName ('The file's current name, exactly'). The description mostly restates these guards rather than adding new parameter meaning, so the high-coverage baseline of 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?

States a specific verb+resource ('batch form of drive_trash_file ... trash') with a precise scope: up to 100 {fileId, expectedName} items in one call. Explicitly names the sibling it is the batch version of, and clarifies boundaries ('Trash only, restorable for 30 days; no permanent delete'). An agent can unambiguously distinguish it from drive_trash_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?

Establishes clear when-to-use context: batch trashing of up to 100 accepted items in a single call, and references the single-tool counterpart ('Same guards as the single tool'). It does not explicitly state 'use drive_trash_file for a single item' or enumerate exclusions, so it stops short of a 5, but the batch-vs-single differentiation is strong.

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