Change app settings

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

Goes beyond the annotations by disclosing that the language change governs EVERY future ad, script, plan and answer, applies to MCP renders as well as the in-app UI, spans all profiles, and takes effect on the next call — context that justifies the destructiveHint. It stops short of stating reversibility or any permission requirements.

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-loads the core action, then documents each of the three parameters in order before the closing scope/timing notes. Dense and mostly waste-free, though the language parenthetical is long relative to the simple enum-style values.

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?

With no output schema and annotations already covering idempotency and safety, the description supplies the parameter meanings, the global scope, and the activation timing an agent needs. Minor gaps remain around reversibility and required permissions, but nothing essential 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 coverage is already 100%, so baseline is 3, but the description adds real meaning: the language must be given as a plain-English name (with examples like "Brazilian Portuguese") and its forward-looking scope, plus the purpose of watchEmail and the allowed theme values.

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 (change) and resource (this account's app settings) plus scope (account-wide, every profile). It is clearly distinct from get_settings by the mutation verb, but it never names the sibling explicitly, so sibling differentiation is left to inference.

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?

'Only pass what you are changing' is a useful partial-update instruction, and the account-wide/next-call notes give context. However, there is no explicit when-to-use guidance or pointer to get_settings as the read counterpart, so usage is only implied.

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