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

With no annotations, the description carries the full burden and does well: it discloses the FIGMA_TOKEN env var auth dependency, that fetching goes through Figma's REST API, determinism, hidden-node skipping, and vector-only frames collapsing to a single leaf. It does not cover error behavior or rate limits, so it falls just short of exhaustive.

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?

Dense but front-loaded, moving from purpose to input modes to return shape to call-site instruction. Every clause carries information; nothing is padding for a five-parameter tool.

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, but the description names the return shape { design, componentMap, viewport }, which covers the gap. Combined with full parameter coverage and the auth/fetch explanation, an agent has what it needs, though the nested `nodes` object shape is left to the raw API response.

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 coverage is 0%, so the description must compensate and largely does: it shows the `url` format with an example, explains `fileKey` + `nodeId` as the alternative, documents `nodes` as a raw GET /v1/files/:key/nodes passthrough, and defines `maxDepth` as depth limit. It does not state precedence if both `url` and `nodes` are supplied, leaving one ambiguity.

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?

Specific verb+resource: 'Turn a Figma frame into the design spec designfit_validate expects.' It names the downstream sibling explicitly, so an agent can place it in the workflow without opening either 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?

It lays out the input modes clearly (Figma URL, or fileKey + nodeId, or paste a raw nodes response with no fetch) and routes to designfit_validate with 'add `url` and call designfit_validate'. No explicit when-not-to-use case, but the alternatives are enumerated.

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

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

With no annotations, the description carries the full burden and does disclose two non-schema behaviors: the page must be instrumented with data-designfit-id before validation, and the tool returns a fidelity score plus a machine-actionable fix-list of token/geometry/presence violations. It omits auth/permission needs and any rate or rendering limitations, but the operational model is largely conveyed.

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?

Three sentences, front-loaded with purpose, then the setup/instrumentation requirement, then the return values. Dense and free of filler; every clause adds information.

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?

There is no output schema, so the description correctly explains what comes back (fidelity score + fix-list). For a 5-param tool with nested objects and no annotations it is largely complete, though it leaves viewport and tolerance controls unexplained.

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 compensate. It meaningfully clarifies that design is a geometry+tokens spec and that componentMap links selectors to figmaNodeId (via the data-designfit-id tagging), but it never mentions viewport or tolerances, leaving two of five parameters semantically undocumented.

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: 'Validate a rendered front-end against its Figma design.' It also distinguishes itself from its sibling by naming designfit_extract as the source of the design spec, so an agent can route between the two without opening either 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?

The description lays out the preconditions for a successful call (tag elements with data-designfit-id, supply the spec, the running URL, and the component map) and points to designfit_extract / Figma's MCP as spec sources. It conveys the workflow clearly but does not state a when-not or an explicit alternative-validation path.

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