google_ads_data

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

Annotations already declare readOnlyHint=true, and the description is consistent with that. It adds valuable behavioral context beyond the annotation: the requirement of a connected data source, how to obtain necessary IDs, and endpoint-specific time windows (e.g., all time vs. last 3 months). This goes beyond the safety profile declared by annotations, though it doesn't cover rate limits or error handling.

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 well-structured: a clear opening statement, a concise prerequisite note, and a bulleted argument list. Every sentence adds value, and information is front-loaded. It is appropriately sized for the tool's complexity.

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?

The tool has 4 parameters and no output schema, so the description must compensate. It covers prerequisites, each endpoint's data types, and time ranges, making it reasonably complete. However, it omits the config parameter and does not describe the exact response format or pagination behavior, which are minor gaps.

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 has zero descriptions, so the description carries the full burden. It explains project_id, account_id, and endpoint thoroughly, including detailed explanations of each enum value with time ranges and data types. However, the 'config' parameter is completely undocumented, leaving a gap in parameter coverage.

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 clearly states the tool queries 'your own Google Ads account data' with a specific list of data types (clicks, impressions, campaigns, keywords, ad copy). This distinguishes it from siblings like google_ads_transparency, which likely handles public ads data, and other analytics tools.

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 provides clear context on when to use the tool (for own Google Ads data) and even lists prerequisites (connected data source, calling list_projects() and list_connections() to get IDs). However, it does not explicitly mention alternatives or when not to use it, so it lacks exclusions.

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