vw_revert_last

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

Annotations confirm a mutating but non-read-only-safe operation (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds real context beyond them: what state is restored, that the effect is scoped to MCP-originated writes only, and that repeated calls step back further. It does not say what happens when there is nothing to revert (error vs no-op), and 'deletes the symbol' sits in mild tension with destructiveHint=false, though the undo framing makes it a restore rather than a destruction.

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?

Three tight sentences, front-loaded with the core action, then the scope of what gets restored, then the repetition and limitation notes. No filler; every clause carries actionable information.

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 zero-parameter, no-output-schema undo operation, the description covers scope, repeatability, and the one major limitation (vw_exec_python edits). Nothing an agent needs to invoke it correctly is missing.

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 tool takes no parameters, so 4 is the baseline. The description correctly implies no arguments are needed and adds no misleading parameter talk.

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 precise verb+resource ('undo exactly the last MCP write in the active document') and immediately scopes it by naming the sibling tools whose effects it reverses (vw_set_record, vw_set_lighting_device_fields, vw_insert_symbol). An agent can distinguish it from vw_exec_python and the setters without opening any schema.

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?

Gives explicit invocation guidance ('Call repeatedly to step further back') and explicit exclusions: raw vw_exec_python edits can't be reverted this way, and Cmd-Z merges consecutive MCP edits so this tool is the fine-grained alternative. This is exactly when-to-use plus when-not-to-use.

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