figma_scan_ds_compliance

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

Explicitly declares 'Read-only — never mutates the file', consistent with annotations. Discloses threshold behavior and return value structure (samples, overflow). No contradictions.

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?

Concise yet detailed, uses numbered list for clarity, front-loads purpose. Every sentence adds value with no redundancy.

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?

Covers tool purpose, behavior, return data (including samples and overflow), and usage instructions. No output schema needed given comprehensive description.

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 covers all 5 parameters with descriptions. Description adds minimal extra value (e.g., default threshold, expectedDs purpose). Baseline 3 is appropriate as schema does the heavy lifting.

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?

Description clearly states it performs a 'Full DS compliance scan for a completed screen' and lists specific return values (coverage, samples, overflow). It distinguishes from sibling figma_validate_screen by noting stricter threshold and granular gaps.

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?

States it's a 'FINAL GATE' for completed screens and instructs Claude to fix violations if passed: false. Implicitly differentiates from validate_screen via default threshold (85 vs 80). Lacks explicit when-not-to-use but context is clear.

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