app_infos__update

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

Annotations (readOnly=false, idempotent=true, destructive=false) already establish the safety profile. The description adds non-obvious behavioral context beyond that: changes propagate to every version because categories are app-level rather than version-level. The PATCH endpoint is also disclosed. No contradiction — 'Change' aligns with readOnly=false and idempotent PATCH semantics.

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, zero fluff: the first states the action, the second delivers the critical scope side-effect, and the endpoint is appended for reference. Every sentence earns its place and the most important constraint is 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?

For a mutating PATCH tool with no output scheema, the description covers the essential effect (propagation to all versions) and the scheema documents the nested payload structure for all six category/subcategory relationships. Minor gaps remain — whether omitting a relationship clears it, and required permissions — but the core call path is well-specified.

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%: id is described as 'ID from the matching list call' and body as 'JSON:API request body (Apple schema: AppInfoUpdateRequest).' With full schema coverage the baseline is 3. The description adds slight semantic value by mapping the abstract relationship fields to the concepts of primary/secondary categories and subcategories, but doesn't clarify partial-update or clearing behavior.

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?

The description opens with a specific verb and resource: 'Change an app's primary and secondary App Store category and its subcategories.' It states exactly what is mutated and narrows the scope versus version-level tools by noting the entity persists 'for every version,' distinguishing it from related siblings like app_store_versions__update and the read-only app_infos__* getters.

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 second sentence gives clear scoping context: categories 'belong to the app rather than to a version,' so this tool is the right choice for app-wide category changes and is implicity contrasted with version-scoped updates. It doesn't explicitly name alternative tools or state when-not-to-use, but the app-vs-version distinction is strong enough to route an agent correctly.

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