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

Annotations declare readOnlyHint=false and non-idempotent, which convey nothing about cost or side effects; the description fills that gap with 'nothing is generated and no credits are spent' and 'No sign-in is needed to prepare' — exactly the pre-flight facts an agent needs. It stops short of the bar for a 5 because it never explains why a tool annotated as non-read-only is nonetheless side-effect free, leaving a small tension unresolved for a careful agent.

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?

Purpose and return semantics are front-loaded in the first two sentences, and the exclusion rules follow in tight, functional sentences. Slightly redundant in re-listing the device aspect ratios already in the schema, but nothing is padding or unstructured.

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 five-parameter preparation tool with a full output schema, the description covers what remains: no-cost/no-generation semantics, no-auth requirement, content-policy limits, and the correct destination for out-of-scope image work. Nothing an agent needs in order to call this correctly and to route users elsewhere 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 description coverage is 100%: theme, style, colors, device (with aspect ratios) and model_id are all documented in the schema with examples and the default model. The description's device list and theme/style mentions restate that content rather than adding syntax, constraints or defaults, 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 (prepare) and resource (wallpaper), enumerates the output variants (phone 9:16, desktop 16:9, tablet 4:3, square) and the inputs (theme + style), and immediately clarifies the non-obvious outcome: 'Returns the settings and the credits required; nothing is generated and no credits are spent.' That last clause is what separates it from the generate_media sibling without needing to name it.

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?

Explicit when-to-use (from a theme and a style, for a device size), explicit when-not (copyrighted characters, franchises, logos, trademarks, celebrities; uploaded/attached/reference images or videos), and an explicit redirect for the excluded cases ('point the user to the Abracadabrax workspace'). The 'text only' constraint and the originality rule are both actionable routing instructions.

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