get_screenshot

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

The description adds a meaningful behavioral constraint (must be imported beforehand for offline access) that annotations do not convey. It does not explain why readOnlyHint=false for a 'get' operation, whether the call triggers a network fetch or cache write, or what error surfaces when the reference is not in the local store; those gaps are only partially offset by the supplied annotations.

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 tight sentences with no filler, and the output-format fact ('PNG image content') is front-loaded ahead of the prerequisite. Slightly under-specified rather than verbose, so it earns its length but could absorb one more sentence on parameter selection.

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?

No output schema exists, so the description reasonably stops at naming the PNG return, and the annotation set covers the safety profile. Given four undocumented optional identifiers and an offline-import state machine, though, an agent still lacks enough to know which combination of url/nodeId/fileKey/snapshotId to supply.

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?

Four parameters (url, nodeId, fileKey, snapshotId) have 0% schema description coverage and no regex/meaning explanation in the description. Critically, all four are optional yet the description never says how an agent should select a screen — none of the semantics are recoverable from the definition.

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: 'Return a downloaded Figma reference screen as PNG image content.' An agent can tell it produces image bytes. However, it never differentiates itself from the near-identical sibling 'figma_get_screenshot' or from 'download_assets'/'figma_export_assets', which leaves real ambiguity about which one to pick.

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 a genuine prerequisite: 'Import the design first for offline access,' which implies this only works against previously downloaded references. But it gives no explicit when-to-use versus the screenshot/asset/export siblings and no statement of when not to use it or what happens if the import step was skipped.

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