begin_undo

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

The description describes a stateful operation that modifies the undo stack ('Everything you do until end_undo collapses into a single undo step'), yet the annotations declare readOnlyHint=true, which typically indicates no state changes. This is a direct contradiction, undermining the agent's trust in the tool's side effects.

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 two sentences, front-loaded with the core action, and includes a concrete example. No unnecessary words, despite the bilingual duplication.

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 one optional parameter and no output schema, the description covers the operation's purpose, scope, and the pairing with end_undo. It could additionally mention cancel_undo or the necessity of closing the transaction, but the current detail is largely sufficient.

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 includes a full description for the only parameter 'label' (coverage 100%). The description adds no extra semantics about this parameter, so the baseline of 3 applies.

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 states a specific verb and resource: 'Open an undo transaction spanning several MCP calls.' It clearly distinguishes the tool from siblings like undo_last and end_undo by describing its role as a transaction opener, not an undo operation itself.

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 gives an explicit use case: 'ideal for multi-step tasks such as building and rigging a character.' It also references end_undo as the necessary closing pair, implying when to use it. However, it does not explicitly mention alternatives like cancel_undo or warn against using it for single operations.

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