scan_design_system

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only 'scan/extract' operation but does not explicitly state that it does not modify the file, what scope it covers (page vs. entire file), or what the returned result looks like.

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?

The description is one concise, front-loaded sentence with no wasted words. It conveys the action and the key output categories in under fifteen 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?

For a simple single-parameter tool, the description is mostly adequate, but no output schema exists and the description does not explain return structure, the optional nature of pageId, or what happens when pageId is omitted. The 'file' vs. 'pageId' wording also introduces slight ambiguity.

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?

The schema already documents the single parameter with 100% coverage, so the description need not add much. It adds no extra semantic detail beyond the schema, and there is a minor mismatch between the description's 'file' and the schema's 'pageId'.

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 states a specific verb ('Scan') and resource ('a file') and lists the extracted outputs ('colors, fonts, spacing, components'). It clearly communicates what the tool does, though it doesn't explicitly differentiate itself from similar siblings like extract_components or get_design_craft_guide.

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?

No guidance is given about when to use this tool versus alternatives such as export_design_specs, get_local_styles, or extract_components. There are no conditions, exclusions, or recommended contexts provided.

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