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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld). The description adds return-shape information the annotations cannot: PNG shown inline plus SVG/PNG links, and the custom=true mode. That is meaningful extra context, though it says nothing about size/rate limits or failure modes.

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 action and output format, with no filler. The parenthetical output detail is efficient, though the custom=true note slightly duplicates the input schema.

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 no output schema, the description carries the burden of describing what comes back, and it does (inline PNG plus SVG/PNG links), which is the key thing an agent needs. It is complete enough to invoke correctly, with only minor gaps around input requirements already covered by the schema.

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%, so the schema already documents country, number, region and custom. The description's 'custom=true draws any text' restates the schema's own parameter description rather than adding new meaning, 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?

States a specific verb and resource ('Draw a license plate as an image') plus the render target ('exactly as openvan.camp renders it'), so the agent knows this produces a visual artifact. It does not, however, explicitly contrast itself with siblings like check_license_plate or get_license_plate_country, which is the natural source of confusion here.

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?

Usage is only implied by the purpose: draw a plate when you need an image. The one explicit guidance is the custom=true example (drawing any text such as a name), which is genuine but narrow. There is no statement of when to prefer this over the plate-validation sibling.

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