figma_run

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

Annotations already declare destructiveHint=true (so agent knows it can modify state) and openWorldHint=true (so agent knows tool can produce novel outputs). The description adds critical behavioral details: it requires 'Capability Catalog approval' (security/governance step), warns that write commands need 'confirm' when write-confirm mode is on (matching input schema confirm param), and discloses the default node tree depth of 3 with a workaround. This goes well beyond what annotations provide, though it could note whether destructive operations are reversible or what gets destroyed.

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, each densely packed with actionable information: the purpose/approval requirement, discovery mechanism for subcommands, and the depth default behavior. Every sentence earns its place with no wasted words.

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?

Given the tool has 4 parameters (100% schema coverage), no output schema, and is a complex execution tool with both read and write capability (destructiveHint=true, readOnlyHint=false), the description covers all critical aspects: command discovery, syntax help, depth defaults, and write-command confirmation. A complete and self-contained description that effectively makes the tool usable.

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% (all 4 parameters have descriptions), so baseline is 3. The description adds value by explaining the args parameter's usage pattern with an example (['canvas','info']), and by linking the confirm parameter to the write-confirm mode context from the description. However, the description could more explicitly map the fileKey parameter's behavior (bare key vs Figma URL) beyond the schema's description.

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 clearly states the tool runs a Capability Catalog-approved engine command, distinguishing it from query/read-only tools. It explicitly references 'Capability Catalog approval' and 'engine command' as the verb+resource pair, and the note about depth default differentiates this execution tool from inspection tools like figma_inspect or figma_reference.

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 provides explicit guidance on when to use: it tells the agent to first discover commands with figma_reference {name:'capabilities'}, advises appending --help for syntax, and gives a concrete example of adjusting depth (-d <n>) when deeper trees are needed. This forms a complete usage flow for an agent.

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