figma_get_node

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

The description goes well beyond the readOnlyHint annotation by disclosing that instances are not expanded, that the result is tied to a snapshot timestamp (exportedAt vs fileModifiedAt), and that local .fig copies can silently carry stale data whose age cannot be determined. It also explains the refresh parameter's effect and the refreshIgnored case. This is rich, actionable behavioral context.

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?

The description is a single dense paragraph, but every clause carries useful information: content list, instance expansion, timestamp semantics, and local-file caveat. It front-loads the tool's primary purpose before diving into snapshot timing. Slightly long but justifiably so for a tool with this much behavioral nuance.

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 data-retrieval tool with no output schema, the description enumerates the returned design aspects and explains the critical freshness limitations that could otherwise mislead an agent. It does not detail the output structure or how to obtain node_id, but the schema's file parameter covers node-id-in-URL, and the listed content areas are sufficient to set expectations. Minor gaps exist around error cases and depth defaults, but these are already in 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?

The input schema already describes file, depth, and refresh, covering 75% of parameters. The description adds meaning for refresh ('pass refresh to export it again') and clarifies the local-file behavior, but it does not explain node_id or depth beyond what the schema/name implies. With partial schema coverage, this is adequate but not exhaustive.

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 clearly states the tool returns 'Detailed design data for a node and its subtree' and enumerates the content (geometry, fills/strokes/effects, auto-layout, text styling, component/instance info). It distinguishes from siblings by noting 'Instances are not expanded', but it lacks an explicit verb and doesn't name alternative tools, so it falls just short of full differentiation.

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?

There is no explicit when-to-use guidance or comparison to sibling tools such as figma_get_tree or figma_get_text. The description provides operational cautions about data freshness ('The result is dated by the copy it answers from', 'pass refresh to export it again') but these are behavioral caveats, not selection criteria. The intended use must be inferred from the tool name and content list.

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