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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the meaningful behavioral fact that the operation persists nothing, which reinforces the preview-only contract beyond what annotations state.

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 tightly packed sentences with no filler; the operation, its content kinds, its design scope and its non-persistence are all front-loaded.

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?

There is no output schema, and the description never states what a preview returns (image bytes, a URL, or a rendered document keyed off the png/svg format enum). For a render tool with nested design/payload objects and no output schema, that return-value gap is the main missing piece.

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 67% and the design object is already documented in the schema. The description compensates by enumerating the accepted payload kinds (url, text, email, phone, sms, wifi, whatsapp, geo, event, vcard), which the schema only gestures at with a single 'kind' example, adding real selection value.

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 ('Render') and resource ('unsaved static QR') and enumerates the ten supported content kinds plus the design aspects being tried (colours, shapes, logo, frame). 'Unsaved' / 'Nothing is stored' implicitly distinguishes it from qrs_create and qrs_get_image, though no sibling is named outright.

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?

The phrase 'to try colours, shapes, logo and frame' implies the preview-before-commit use case, and 'Nothing is stored' signals it is a dry run. However, it never explicitly says when to prefer this over qrs_create or qrs_create_from_template, so the routing is left to inference.

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