trash_nodes

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

The single destructiveHint annotation only tells the agent this is a write; the description goes far beyond it by disclosing soft-delete semantics, a 30-day retention default, in-app undo via activity log, all-or-nothing atomicity, a success-only return, the files:delete permission requirement, and the idempotency_key retry pattern. These are the operational facts an agent needs before mutating data.

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?

Four dense sentences, front-loaded with the core action, followed by safety semantics, then the alternative tool, then prerequisites. Nearly every sentence earns its place; only 'returns success' is slightly redundant against the output schema, and the all-or-nothing clause is terse to the point of being clipped.

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 destructive two-parameter mutation with only a destructiveHint annotation, the description supplies everything an agent needs: reversibility, retention window, atomicity, permission scope, retry safety, and the sibling to use for dry runs. Return values are covered by the existing output schema, so nothing material 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 baseline is 3, but the description earns more: it clarifies that node_ids may be files OR folders and that folder contents are included recursively, and it explains the purpose of idempotency_key (making retries safe) beyond the schema's bare 'stable retry key' text. Minor remaining gap: no mention of practical batch-size limits.

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 and resource — moving files or folders (with recursive contents) to the trash — and immediately distinguishes it from siblings by naming list_trash, restore_nodes, and batch_nodes. An agent can identify the exact operation 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?

Explicitly routes the agent: use this tool for bulk trash with all-or-nothing semantics, but use batch_nodes instead when per-item results or a dry-run preview are needed. It also names the recovery path (list_trash / restore_nodes), so the agent understands the downstream workflow.

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