Run design QA

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

Without annotations, the description carries full burden. It describes the sequential execution and failure return, but lacks details on side effects (e.g., where the HTML report is stored), output on success, or potential rate limits. The description is adequate but not thorough.

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 two sentences, front-loaded with the primary purpose, then details on execution and failure handling. Every sentence adds value, and it is efficient.

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's complexity (runs 4 sub-tools) and lack of output schema, the description is somewhat incomplete. It explains the sequence and failure return, but does not specify the success return value or where the HTML report is output. This leaves uncertainty for the agent.

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 100%, providing baseline 3. The description adds context: 'Give it a Figma frame link' for figmaUrl, 'URL of the built page' for buildUrl, and mentions viewportWidth defaults to the Figma frame width. This adds meaning beyond the schema.

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's purpose: 'End-to-end design QA: measures a Figma frame and a live page, then writes an HTML report.' It also distinguishes itself from sibling tools by explaining it runs a sequence of those tools (capture_design, capture_build, check_tokens, build_report) in one call.

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 clear usage guidance: 'Give it a Figma frame link and the URL of the built page.' It also explains the sequential execution and fallback behavior: 'On failure it returns the runId so the remaining steps can be run individually.' This helps the agent decide when to use this composite tool versus running individual steps.

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