update_localization

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description usefully adds the external constraint that Apple gates edits on version state, which is context the annotations cannot convey. It does not clarify the more consequential behavior implied by destructiveHint — whether omitted keys in 'attributes' are cleared versus preserved, and whether the mutation is revertible.

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 short sentences, mutation warning front-loaded, zero filler. Nothing is wasted or buried.

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?

This is a destructive, non-idempotent mutation with a nested payload, zero schema descriptions and no output schema, so the description carries a heavy burden. It omits partial-update semantics, whether the call returns the updated localization, and how to recover from a version-state rejection — the gaps an agent would most likely hit when invoking it.

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 0% for two required parameters, including a nested 'attributes' object with six properties, and the description adds no meaning to either localizationId or any attribute field. Given the nested, partially-specified payload, the description should at minimum indicate that 'attributes' is a partial set of localizable fields and what happens to fields left out.

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 names a specific verb (MUTATES) and a specific resource (App Store version metadata for a localization), which is enough to separate it from create_localization and update_app_info_localization in principle. It stops short of explicitly naming those siblings or saying 'version localization, not app-info localization', so an agent must infer the distinction from the phrase 'version metadata'.

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?

'Apple may restrict edits based on version state' gives a useful precondition for when the call will succeed. However, it gives no guidance on choosing this tool over update_app_info_localization or create_localization, and no instruction on what to do when the edit is rejected (e.g. check version state first via get_version).

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