Read a Figma kit

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description goes well beyond that by disclosing the concrete side effect (a JSON file written to outputPath), the return shape (counts), the human-in-the-loop confirmation requirement, the plugin-open prerequisite, and that passing projectId overwrites the kit the project previously held. That is the full behavioral picture an agent needs before invoking a mutating, open-world tool.

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?

Four sentences, front-loaded with the core action and the item inventory, then prerequisites, then the optional persistence behavior. Nothing is filler, though the final sentence is dense and stacks two distinct ideas (persistence and downstream naming) that could be split for faster scanning.

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?

An output schema exists, so return values need not be spelled out, yet the description still adds the useful 'returns the counts' cue. Combined with the plugin/confirmation prerequisites, scope boundary, and side-effect disclosure, an agent has everything needed to call this correctly on a two-parameter open-world tool.

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 meaning: projectId is not just storage, it causes later calls to build with the client's own names and values, which the schema's 'replacing the one it held' does not convey. outputPath is left entirely to the schema, which already documents relative-path resolution.

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 opens with a specific verb and resource ('Reads the design kit in the Figma file the designer has open') and enumerates exactly what is captured: variables across all modes, text and effect styles, and components with variant options. It clearly bounds the scope ('only the file's own items are read; a library is read from its own file'), which distinguishes it in spirit from extract-design-system / get-design-system-kit, but it never names a sibling outright.

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?

Preconditions are explicit: the Better Design plugin must be open in that file and the designer must confirm the read in the panel. It also explains the optional projectId path ('so later calls build with the client's own names and values'). What is missing is any explicit routing versus alternatives such as extract-design-system or get-design-system-kit, so the agent must infer which to call.

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