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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds meaningful behavioral context: it is project-scoped (does not rely on the active project pointer), returns the project identity with the result, and behaves differently for window-patch (instant) vs legacy whole-file erases (rebuild). This goes beyond the annotations without contradicting them.

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 with the critical scoping constraint ('PROJECT-SCOPED'). It then explains the action, parameter behavior, and performance characteristics in a logical order without redundancy. Every sentence adds value, making it an efficiently structured description.

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 tool with only two parameters and no output schema, the description covers the core operation, scoping, parameter semantics, and performance. It even hints at the return value ('returns the project identity with its result'). It does not detail the exact return format, but that may not be necessary given the simple operation and the presence of related tools like project_state.

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 50%: only project_id has a schema description, while id has none. The description compensates by explaining that id is the erased region identifier (optional, see get_edl) and that omitting it undoes all erases. This adds essential meaning to the id parameter that the schema lacks.

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 clearly states the action: undo an erase, restoring original pixels. It specifies the resource (erase) and distinguishes it from siblings like erase_region and other remove_* tools by focusing on undoing an erasure operation. The scoping to project_id is also explicit.

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 provides context on when to use it: to undo an erase, with the option to target a specific region by id or all erases when id is omitted. It also mentions performance differences between window-patch and legacy whole-file erases, helping an agent set expectations. However, it doesn't explicitly state when not to use it or name alternatives, relying on the tool name and siblings for that.

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