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

Goes well beyond the annotations (readOnly/idempotent/openWorld) by disclosing that the photo is processed in memory and discarded server-side, how status outputs (needs-review/failed) map to action, and a hard constraint against predicting a grade.

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?

Front-loaded with purpose, then preconditions, privacy note, input options, fallback, and status handling. Every sentence is actionable and none repeats another.

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?

With an output schema present the description needn't explain return values, yet it still clarifies status meanings and the acceptable input forms. Nothing needed to invoke it correctly is missing.

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%, including detailed descriptions for face, image_url, and image_base64, so the baseline is 3. The description's 'public HTTPS URL or image bytes' and 'ask front or back' largely restate the schema and add no card_size detail.

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?

States a specific verb and resource ('Measure ... card centering from one photograph') and even names the exact metric reported ('worst-station left/right and top/bottom'). The closing rule 'Never predict a final grade' implicitly separates it from the grade_centering sibling.

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?

Gives explicit preconditions ('Ask front or back before calling'), photo requirements (whole card, flat, dark surface, straight from above, out of sleeve), and a concrete fallback (send user to the website if an attachment cannot be passed). Also tells the agent what to do on needs-review/failed.

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