Undo (dangerous)

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the critical nuance they cannot: it reverts to the plugin's checkpoint, discarding hand edits made since the last tool call. It also discloses the confirm:true precondition and per-editor verification status (Design verified; FigJam, Slides unverified).

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?

Front-loads the core action, immediately follows with the WARNING, then the safer alternative, the precondition, and editor support. Dense but every clause carries distinct, load-bearing information with zero filler.

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 destructive mutation tool with no output schema, the description covers the action, the data-loss risk, the safe alternative, the required confirmation, and platform caveats – everything an agent needs to decide and call correctly.

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 100%, so count, confirm, session, and idempotencyKey are all already documented in the schema. The description only reinforces the confirm requirement, adding no syntax or meaning beyond what the schema provides. Baseline 3 is appropriate.

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 target ("Trigger Figma's undo") plus the exact behavioral scope: it returns to the plugin's last committed checkpoint. This is unambiguous and clearly distinct from all the create/delete/mutation siblings.

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?

Explicitly names the preferred alternative (figma_delete_nodes with ids a create call returned) and the condition that selects it (undoing agent work safely). It also states the when-not case: hand-made user changes will be lost. Nothing is left to inference.

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