Create from spec

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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), but the description adds substantial non-structural behavior: unknown fields are 'refused, never dropped'; a mid-way failure does NOT roll back and reports created[]/failedAt; idempotencyKey is needed for safe retry on large specs; and editor support is scoped (Design verified; FigJam/Slides unverified). This is far beyond what annotations convey.

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?

Dense but front-loaded: the capability statement comes first, then workflow, then grammar pointer, then the minimal shape, then failure/idempotency semantics, then editor scope. Every sentence carries operational value, though the grammar pointer plus inline example is slightly redundant.

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 complex single-call section builder with no output schema, this is complete: it gives the grammar source, a worked minimal example, the multi-call workflow, failure semantics, retry guidance, parent/page placement rules, and editor support. An agent could invoke it correctly without opening other docs.

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% and each of the 5 params has a schema description, so the baseline is 3. The description does add value by giving a minimal shape example, stating that an array of roots needs parentId or pageId, and explaining why idempotencyKey matters — but the core grammar is delegated to figma_get_guide rather than fully specified here.

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 (build a whole section in one call) and enumerates exactly what it can produce — header, hero, card, grid, footer — plus the node types it supports. This clearly distinguishes it from the granular siblings like figma_create_frame, figma_create_text, figma_create_rectangle that build single nodes.

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?

Explicit when-to-use workflow: 'a wrapper frame, then one call per section into it by parentId; after each, figma_check_layout and one figma_export_node, then targeted fixes.' It also states the alternative boundary — 'Not a whole page in one payload: a section at a time' — and points to figma_get_guide for the grammar, routing the agent precisely.

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