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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real context beyond that: the link is free, runs on-device, and needs only one photo — which implies no data upload. It stops short of describing what the link returns or any constraints on the resulting measurement.

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?

Two sentences, front-loaded with the core action and scoping, with no filler. The parenthetical value list slightly duplicates the enum, costing a little efficiency but it aids scanning.

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 one-parameter, read-only tool with no output schema, the description covers what is returned (a link) and the trigger. Missing only the fallback routing to sibling lookup/classification tools, which is a minor gap given the simple surface.

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% and the single enum parameter is fully documented, so the baseline is 3. The parenthetical lists the exact enum values (PSL, face shape, canthal tilt, facial ratios), which merely restates the schema rather than adding format or selection meaning.

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 uses a specific verb+object ('Return the link to FaceRuler's free on-device tool') and scopes it to measuring a real face from one photo. It implicitly distinguishes itself from the lookup/classify siblings by being a tool-link provider, but never names those siblings, so the boundary with psl_score_lookup and classify_face_shape is left to inference.

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?

It gives a clear trigger: 'Use when the user wants their own face measured.' That is a usable condition, but there is no guidance on when NOT to use it (e.g., when the user wants an existing score looked up or a shape classified instead), so the agent must infer the alternative.

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