maps_set_search_rating

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

With no annotations provided, the description carries full disclosure burden and delivers richly: it reveals that expectedQuery is revalidated immediately before each action, the rating is restricted to a live-observed subset, post-conditions include both a visible chip (with exact format example) and a closed Rating menu, the search query is preserved, and Interactive Assist must be enabled. This is exemplary behavioral transparency for a UI-interaction tool.

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 dense sentences with zero fluff — the first front-loads the action, the second covers verification and preconditions. Every clause adds information: 'bounded', 'revalidated', 'for example 4.0+', 'closed Rating menu', 'preserving the expected search query', and 'Interactive Assist must be enabled' all earn their place.

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 2-parameter filter tool with no output schema and no annotations, the description covers the action, parameter constraints, post-conditions, verification behavior, and a runtime prerequisite. Absent any need to explain return values (no output schema) or complex nested structures (no nested objects), this fully equips an agent to use the tool correctly.

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?

Despite 0% schema coverage, the description adds meaningful semantics beyond the schema: expectedQuery's revalidation requirement, the 'observed half-step' nature of the enum values, and the exact chip format ('4.0+') as an example. It could have gone further explaining what 'observed' means operationally, but it substantially compensates for the missing schema descriptions.

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 uses a specific verb+object construction ('Apply... Rating filter option to the active search result view') and is clearly differentiated from sibling set_* tools like maps_set_transit_time and maps_set_travel_mode. The qualifiers 'bounded' and 'live-observed' add useful scope that distinguishes this tool's behavior from a generic rating filter.

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 context that this tool operates on 'the active search result view' and implies workflow usage by noting the query is preserved and revalidated, which tells agents when it's safe to invoke. However, it doesn't explicitly name alternatives or state when-not-to-use, so it stops short of the top score for explicit exclusions.

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