Rollback Edits

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

The description explicitly discloses the destructive scope ('every uncommitted change') and the additional side effect of closing the edit session, which goes beyond the destructiveHint annotation. It provides helpful detail about what will be lost.

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 a single, clear sentence with no filler, front-loading the action and outcome.

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 simple tool with one parameter and no output schema, the description covers the operation's effect and side effect. It doesn't explicitly mention prerequisites like needing an active edit session, but this is implied and not a significant gap given the sibling tool names.

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 description says 'on a layer,' which maps directly to the layer_id parameter, but it provides no further detail about the parameter format or how to obtain the ID. With 0% schema coverage, the description offers only minimal compensation beyond the parameter name.

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 uses a specific verb ('Discard'), identifies the resource ('layer'), and states the scope ('every uncommitted change') plus a side effect ('close the edit session'). This clearly differentiates the tool from siblings like undo_edits (which undoes individual changes) and commit_edits (which saves changes).

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 clearly implies the use case—when you need to discard all uncommitted edits and end the editing session. However, it does not explicitly mention alternatives or exclusions, such as 'use undo_edits to revert specific changes instead.'

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