undo

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

No annotations are provided, so the description carries the full burden, yet it discloses almost nothing: not whether the undo is itself reversible via redo, what happens if there is no prior edit, whether history is shared or per-project, or what the response contains. Only the single-step scope is inferred from 'the last edit'.

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?

One front-loaded sentence with no filler, so nothing is wasted, but it is under-specified rather than appropriately sized for a tool with zero annotation and zero schema-description coverage.

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?

The tool is simple (one parameter, no nested objects, no output schema), so a short description is defensible, but with no annotations and 0% parameter coverage the agent is left guessing about the 'project' argument format and the failure behavior of undo.

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 0% and the sole required parameter 'project' is never mentioned in the description. It is unclear whether this is a project ID, name, or whether it selects which project's undo stack is popped — a meaningful ambiguity for an undo operation.

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 ('Undo the last edit'), and 'the last edit' scopes it to a single-step reversal, which distinguishes it implicitly from the sibling 'redo'. It stops short of explicitly naming redo/history as the alternatives, so it falls just below the top score.

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?

There is no when-to-use guidance beyond the implicit semantics of the word 'undo'. The description never mentions the sibling 'redo', never says whether repeated undos are possible, and gives no preconditions (e.g., that edit history must exist).

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