See the design

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

Annotations already establish readOnlyHint=true and destructiveHint=false, and the description adds a meaningful guarantee beyond that: 'Nothing is stored anywhere.' It doesn't discuss output format details, but the returned picture behavior is stated directly and no annotation contradiction exists.

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?

Two short sentences with no filler. The core rendering behavior is front-loaded, and the second sentence adds a distinct privacy/durability signal rather than repeating the annotations.

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 simple two-parameter, read-only tool with a documented result ('returns the picture itself'), the description, schema, and annotations together cover everything an agent needs. No output schema exists, but the essential return semantics are stated explicitly.

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 nodeId and scale are already documented in the schema. The description adds nothing about how scale behaves or what nodeId refers to, but it also doesn't have to compensate for missing schema information.

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?

The description states a specific action ('Renders one node') and a concrete result ('returns the picture itself'), so an agent knows exactly what the tool produces. It doesn't explicitly name a sibling tool or contrast with one, but the 'rather than read a description' phrase hints at the alternative.

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?

The intended context is implied: use this when a 'model that can see' needs to inspect the visual design instead of a textual description. However, there is no explicit guidance on when to prefer this over siblings like figma_extract or figma_get_tree, and no exclusion conditions.

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