gdrive_undo

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

With no annotations, the description carries the behavioral burden. It discloses the operation, the token prerequisite, and the supported mutation types. However, it does not explain what 'undo' means per operation type, whether the action is destructive or reversible, or how failures or invalid tokens are handled.

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?

The description is compact and front-loaded: the core purpose appears in the first sentence, and the supported tools and token explanation follow without repetition or fluff. Every sentence earns its place.

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 single-parameter tool, the description provides a workable baseline: what it does, which operations it supports, and where its input comes from. But because there is no output schema and no annotations, the agent is left without guidance on per-operation undo semantics, error behavior, idempotency, or expected return values.

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?

The schema only defines restore_token as a required string, so schema description coverage is 0%. The description compensates by stating that the token is returned by a mutating gdrive_* tool after commit, giving the agent concrete provenance and validity context. It stops short of describing token format or exact response field names, so a 4 is appropriate.

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 opens with a specific verb and resource: 'Undo a prior Drive mutation using its restore_token.' It also lists the exact sibling tools it can undo, which clearly distinguishes it from gdrive_rename, gdrive_move, gdrive_trash, and the other mutation tools in the sibling list.

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 supported-tools list and the requirement that restore_token come from 'a mutating gdrive_* tool after commit' give the agent clear context for when to invoke this tool. It does not explicitly state when not to use it, but the undo scope is specific enough that alternatives are implicitly identified.

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