Measure Screenshot

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

Annotations already supply readOnlyHint=true, idempotentHint=true and destructiveHint=false; the description complements these by disclosing operational behavior: 'Reads the local file you name; makes no network call' (scope/privacy), 'PNG only' (input restriction), and the markdown/HTML output modes. The description is fully consistent with the annotations — no contradiction.

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, each earning its place: measurement capabilities, output formats, constraints/privacy, then workflow routing. The most decision-relevant information (what it measures, PNG-only, no network) is front-loaded, with zero tautology or filler.

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 complex tool with no output schema, the description covers the essentials: measured dimensions (with confidence levels), returned artifacts (markdown, optional HTML), input constraints (PNG, local path), and workflow placement ('before critiquing a UI'). The return format is described narratively rather than structurally, and failure behavior for invalid paths is left unspecified — minor gaps given the strong schema coverage.

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% and each parameter is already richly documented — path (absolute paths preferred, working-directory caveat), scale (Retina/2× pixel-ratio logic), format (markdown/html/both semantics), max_colors (cluster count, default 12). The description narratively reinforces the format behavior ('on request, a self-contained HTML report') but adds no genuinely new parameter meaning beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb and resource — 'Measure a real screenshot from its actual pixels' — and enumerates the exact outputs: palette, distinct colour count, WCAG contrast ratios, whitespace/density, and structural detections with confidence levels. No sibling tool measures screenshots; fix_contrast and audit_design_system are explicitly positioned as companions, not competitors, so the definition fully disambiguates the tool.

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?

Explicitly states when to invoke it: 'Use it before critiquing a UI so the review cites measured numbers instead of impressions.' It also routes to the right companion tools — fix_contrast for failing pairs and audit_design_system for the codebase behind the screen — and states hard constraints (PNG only, local file, no network call) that shape when it applies.

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