figma_get_design_system_kit

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

No annotations exist, so the description carries the full burden and does so: it discloses adaptive compression triggered by response size regardless of the format setting, delta-encoded variant specs (base carries full visualSpec, siblings carry only diffs), image inclusion as a latency cost, and a non-obvious infrastructure dependency (Desktop Bridge/cloud relay, plan-independent). These are exactly the traits an agent cannot infer from the schema.

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?

Front-loaded with the routing decision, then layered into payload, encoding scheme, infrastructure, and error recovery — a sensible order. It is dense but slightly repetitive on compression ('adaptive compression for large systems' is restated as auto-compression in the schema) and the AI-code-generation sentence is soft value framing rather than operational detail.

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?

With no output schema and five parameters, the description compensates fully: it describes the return shape (tokens/components/styles plus visualSpec and screenshots), the variant delta structure, and the failure mode with recovery steps. An agent has everything needed to call it correctly and interpret the 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 100%, so the baseline is 3, but the description adds genuine semantics beyond it — the compression behavior that overrides 'format', and the delta-encoding rule that explains what 'summary' actually strips. Minor gap: it does not clarify fileKey inference behavior or the interaction between componentIds and include, though the schema covers those.

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?

Names a specific verb+resource ('design system extraction') and immediately scopes it against three named siblings (figma_get_styles, figma_get_variables, figma_get_component). The returned payload is enumerated concretely (tokens, components, styles, visualSpec, screenshots), so an agent can distinguish it from the many other Figma read tools without opening the 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?

Explicitly states when to use it ('PREFERRED TOOL', 'Use this instead of calling individual tools to avoid context window overflow'), names the exact alternatives it replaces, and gives a conditional fallback for the 403 plan-limited case with a concrete remedy (ensure bridge connected and retry). This is the strongest form of routing guidance in the corpus.

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