ad_manager_google_get_keyword_ideas

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

The description does not contradict the annotations (readOnlyHint=true, destructiveHint=false), so there's no contradiction. However, it adds no behavioral detail beyond what the annotations already imply (i.e., it's a safe, read-only operation). It fails to state what the tool returns (e.g., a list of keyword ideas, relevance scores, volume data) or how inputs like URL and keywords are used. With annotations covering the safety profile, the description should still provide context about behavior, but it doesn't.

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 a single, under-specified phrase. It is not concise in a meaningful way; it omits necessary operational details. The text 'Get keyword ideas' is almost tautological with the tool name, providing no additional structure or information. An effective description would front-load the purpose and then add usage or behavior context.

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 5 parameters, no output schema, and only a minimal description, the tool is insufficiently documented. An agent cannot determine the return format, the intended use of each parameter, any prerequisites (e.g., Google Ads integration must be set up), or how the tool relates to other keyword-targeting tools. The description leaves too much to inference for a tool with this complexity.

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?

The schema covers all 5 parameters with descriptions (100% coverage). The description offers no additional parameter semantics, but since the schema already documents each parameter, the baseline of 3 applies. The description doesn't need to repeat parameter info, but it could have clarified relationships between URL, keywords, and locations.

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 states a clear verb ('Get') and a resource ('keyword ideas'), which is a specific action on a resource. However, it doesn't elaborate on what 'keyword ideas' means (e.g., generated from a URL or seed keywords) or how it distinguishes from other Google Ads tools like ad_manager_google_get_target_interests. It is clear but generic, so it earns a 4 rather than a 5.

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?

There is no guidance on when to use this tool versus alternatives. It doesn't mention ideal scenarios (e.g., when you have a URL to derive keywords), what to do if the URL is missing, or what types of inputs are mutually exclusive. Agents receive no context for selecting this tool over similar Google Ads tools.

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