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

Annotations declare the write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), and the description usefully adds that output is hosted files and does not edit the caller's project — a non-obvious scope boundary. It does not, however, explain the non-idempotent behavior (repeat calls create new artifacts) or the auth/rate-limit role of apiKey beyond what the schema already says.

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 the use case, then outputs, then a behavioral caveat, then routing — a logical order with no filler sentences. The output enumeration is long but each item conveys what gets produced, so it earns its space.

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 an 11-param, open-world, non-idempotent generation tool with an output schema, the description covers the trigger, the source forms, the produced artifacts, and the scope boundary. Remaining gaps (enum semantics for variantType/backgroundShape, idempotency) are modest since the output schema handles return values.

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 55%, and the description reinforces the source parameter's accepted forms ('one image, URL, or Iconify name') and loosely maps to includeThemeAwareFavicon ('theme-aware icons') and includeDevVariations ('environment variants'). But several params (variantType, backgroundColor, backgroundShape) have no schema description and no explanation here, so the description only partially compensates for the coverage gap.

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 (generates) and resource (a favicon/app-icon set) and then enumerates the concrete artifacts produced (favicon.ico, PNG sizes, Apple/Android icons, manifests, install snippet). It also distinguishes itself from the sibling search_icons, so an agent can separate it from alternatives without opening a schema.

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 opening sentence gives a strong, explicit trigger list ('create, replace, or install favicons, website icons, Apple touch icons, PWA icons, or app icons') and routes to search_icons with a condition ('if you need a source'). It lacks an explicit when-not and never addresses the check_favicon sibling, so it falls just short of a full 5.

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