undo_workspace

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses bracketing (batch edits come back in one undo), interleaving of user history, redo history clearing on next edit, and the silent no-op on empty history. This goes far beyond what the schema or annotations could convey.

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 well-structured with a one-line summary, a critical warning, and a clear args list. Every sentence adds value—from the Ctrl+Z analogy to the interleaving caveat to the redo behavior. It is appropriately sized for the tool's complexity and front-loaded with the core purpose.

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?

Given the tool's moderate complexity and no annotations, the description is remarkably complete. It covers the main behavior, edge cases (empty history, steps=0), redo semantics, and client scoping. The output schema exists, so return values need not be described. No obvious gaps remain.

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%, so the description must explain the parameters, and it does so completely. It defines steps (1-50, with 0 as a special depth check), redo (step forward, cleared by next edit), and client_id (which tab, defaulting to most recently focused). Each parameter receives meaningful behavioral context that the bare 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 opens with a specific verb and resource: 'Undo the last edit in the browser, exactly as Ctrl+Z would.' This clearly distinguishes it from sibling tools that set, run, or load workspace state. It also immediately conveys the tool's scope and user-facing analogy.

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 explains when to use undo (to cheaply take back wrong edits) and even warns about caution when stepping back multiple times ('several steps back is taking back whatever was there, theirs included'). It also describes redo usage. However, it does not explicitly name alternative tools or state when not to use it, so it stops short of a 5.

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