Import image

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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true), and the description layers on genuinely useful behavior: accepted formats (PNG/JPEG/GIF), the 4096 px per-side limit, what placement does to the target node (becomes its fill vs creates a rectangle), and editor support ('Design; unverified: FigJam, Slides'). It omits retry/idempotency semantics, which live only in the schema field text, so it is not fully self-contained.

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 and keeps everything to a single dense passage with no filler sentences. The heavy em-dash and parenthetical nesting makes it slightly harder to scan than ideal, but each clause carries distinct information rather than restating the name or schema.

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 16-parameter mutation tool with a nested object and no output schema, it conveys the decision points an agent needs: source selection, placement behavior, format limits, and environment support. The remaining omissions (position/name params, idempotency guidance) are minor and partly carried by the schema.

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?

Against 50% schema coverage it compensates on the differentiating parameters: it explains how url, path and renderNodeId differ in who fetches/reads the bytes, that nodeId turns the image into a fill, and that width/height govern the new rectangle. Several params (x, y, name, parentId, cornerRadius) remain undocumented in both description and schema, leaving a real gap.

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 ('Place a picture') and immediately enumerates the three input modes (url, path, renderNodeId) plus the two placement outcomes (fill an existing nodeId vs create a new rectangle). It cleanly distinguishes itself from siblings like figma_export_node and figma_create_rectangle without the agent 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 conditional routing: 'To look at a layer yourself, figma_export_node returns its picture to you instead of placing it' names the alternative and the condition that selects it. It also explains what each source mode does, giving clear context for which parameter to reach for. It stops short of stating hard exclusions (e.g., when not to use a url vs a render), so it is strong but not exhaustive.

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