Batch edits

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

Annotations only declare readOnly=false, destructive=false, idempotent=true, openWorld=false. The description goes far beyond: stop-at-first-failure with no rollback, partial.steps/partial.failedAt semantics, whole-batch Ctrl+Z undo, the 1–50 step limit, pre-flight validation of each step against its own tool parameters, and the BRIDGE_PROCESS motion gate. This is exactly the extra behavioral context the annotations cannot carry.

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 value (ONE call, ONE undo) and the create/delete exclusions before the mechanics. Everything present earns its place, though the single dense paragraph packs success/error shapes, validation, and the motion gate together, which costs some scannability.

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?

This is a complex aggregator tool with no output schema, so the description carries the full burden of describing returns — and it does: the success object shape, the itemsFailed array, and partial failure reporting. Combined with the step format and exclusions, an agent has everything needed to invoke it 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: op names must omit the figma_ prefix, the 1–50 step range, and that each step is validated against its own tool's parameters before execution. Session and idempotencyKey are left to the schema, which documents them adequately.

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+resource ('several edits in ONE call and ONE undo step') and scopes the resource precisely: fills, strokes, radius, effects, auto-layout, sizes, text, constraints, names. It also distinguishes itself from siblings by explicitly excluding creates (naming figma_create_from_spec), deletes, and node-replacing ops (group, boolean, flatten, clone), so an agent can differentiate it from hundreds of siblings without reading a 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 when-to-use ('a polish pass over what you built'), when-not (no creates, no deletes, nothing that replaces nodes with new ids), and names the alternative for the excluded case (figma_create_from_spec builds). It also flags the motion-gate prerequisite for keyframe steps, so the agent knows exactly what conditions apply.

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