get_design_context

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

The description usefully clarifies that this MCP does not execute skills or generate code, which meaningfully sets expectations beyond the annotations. However it says nothing about whether a url, fileKey, nodeId, or snapshotId is required to get a result, how depth/limit affect the response size, or what the openWorldHint=true lookup implies. With annotations present the safety bar is lower, but the input-resolution behavior remains opaque.

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, front-loaded with the core action and defaults before the optional profile. Every clause carries information; only "Get design data" is vague enough to be weak.

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 seven-parameter tool with a nested object, no output schema, and zero schema descriptions, the description is far from sufficient. It omits how the target is identified (url vs fileKey+nodeId vs snapshotId), what depth and limit control, and what the returned design data looks like, so the agent must guess at call shapes.

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 0%, so the description must carry the burden and largely does not: url, depth, limit, nodeId, fileKey, and snapshotId are never explained, nor is their interplay. Only the implementation sub-object gets real meaning added (platform/framework, component strategy and library, preferred client skills), which covers a minority of the seven parameters.

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 says it retrieves design data plus implementationGuidance, which names a verb and a resource, but "design data" is broad and it never distinguishes itself from the near-identical sibling figma_get_design_context or from get_metadata. An agent cannot tell from the text which of the two design-context tools 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?

It states defaults (native OS bars, project components) and that the implementation profile is optional, which implies the common case, but it gives no explicit when-to-use, no when-not-to-use, and no pointer to alternatives among the many sibling retrieval tools. Anything about picking this over get_screenshot or get_metadata must be inferred.

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