Change app settings

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

Annotations already declare readOnlyHint=false and idempotentHint=true, and the description does not contradict them. It adds valuable behavioral context: the language setting persists to every future ad/script/plan/answer and also applies to MCP renders, and changes 'take effect on the next call.' These details go beyond the structured annotations and clarify the operation's persistence and timing.

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?

The description is longer than a two-liner but every sentence earns its place by explaining parameter behavior, scope, and side effects. It is front-loaded with the core purpose and then systematically walks through each setting. It could be tightened slightly by removing minor redundancy (e.g., the language example list), but overall it remains efficient and well-ordered.

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 simple update tool with three optional parameters and no output schema, the description covers the necessary ground: what each parameter does, the account-wide scope, the 'only pass what you are changing' pattern, and timing. It does not spell out the return value, but no output schema exists and the behavior is straightforward. The annotations provide the safety profile, so nothing critical 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%, so the baseline is 3. The description adds meaning beyond the schema: for language it specifies that it applies to EVERY ad, script, plan and answer, gives plain-English formatting examples, and notes MCP render applicability; for theme it reiterates 'dark' or 'light'. This is substantial enrichment, especially for the language parameter, though watchEmail adds little beyond the existing schema description.

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 the specific verb-resource pair 'Change this account's app settings', immediately distinguishing it from brand-level or content tools. It then enumerates the three settings it changes with precise meanings. The 'Account-wide (every brand)' phrase also differentiates it from sibling tools like update_brand, leaving no ambiguity about the target resource.

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 description gives clear scope ('Account-wide (every brand)') and instructs 'Only pass what you are changing', which tells the agent when and how to invoke it. It stops short of explicitly naming alternatives, such as 'use update_brand for brand-specific settings,' so there is no direct when-not-to-use statement, but the account-wide qualifier strongly implies the boundary.

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