Flatten

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

Annotations cover safety/idempotency, and the description adds real domain behavior: the shared-parent requirement, the undo limitation ('Cannot be undone except with Ctrl+Z'), and editor support scope (Design only, FigJam/Slides unverified). The undo caveat sits slightly in tension with destructiveHint=false but is reconcilable since Ctrl+Z restores state.

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 what the tool does, then the precondition, then the irreversibility warning and platform scope. No filler or restatement of the tool name.

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 mutation tool with annotations present and no output schema, it covers the crucial operational facts (parent constraint, undo caveat, editor support). Minor gaps remain: the effect of the 'name' parameter and whether child styles/attributes survive the merge.

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 50%: session and idempotencyKey are documented in the schema, while name and nodeIds carry no description anywhere. The description contributes only indirectly (the shared-parent constraint on nodeIds) and says nothing about the 'name' parameter or how many nodes can be flattened beyond the schema's maxItems.

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 resource ('flatten nodes into one editable vector') and clarifies the outcome ('a single path'), which implicitly separates it from figma_group_nodes, figma_ungroup_nodes and figma_boolean_nodes. It stops short of naming those siblings, so the distinction is inferable rather than explicit.

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?

Provides concrete triggers ('for a finished icon or a boolean shape that should become a single path') and a hard precondition ('They must share a parent'). It does not state when NOT to use it (e.g. when you still need separately editable child shapes), so alternatives remain unaddressed.

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