google_ads_run_readonly_rpc

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly states that the operation is an enum, that arbitrary paths are impossible, and that all mutations/uploads are impossible. This meaningfully informs the agent about safety and flexibility boundaries, though it does not cover rate limits, auth requirements, or response behavior.

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 compact and front-loaded with the most important scoping statement ('read-only escape hatch... outside GAQL'). The long list of services and the explicit safety constraint are useful, though 'Advanced' adds little and the sentence is dense.

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 complex RPC-based tool with no output schema and no annotations, the description provides a good high-level map of what it can access and constrains it to safe read-only operations. However, it lacks guidance on how to choose among the 29 operations, what request fields each operation expects, or what the response structure looks like, leaving the agent to rely heavily on the operation names and external API knowledge.

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 67%, with request and customerId already described in the schema. The description adds service-area context that helps interpret the enum operations (e.g., Audience Insights vs. invoices), but it does not map specific operations to specific request shapes or explain how to construct the request object for the listed RPCs.

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 identifies the tool as a read-only RPC escape hatch for Google Ads services outside GAQL and enumerates the specific service areas it covers (Audience Insights, Reach Planner, benchmarks, etc.). It distinguishes itself from the GAQL-based sibling tools by explicitly marking itself as outside GAQL and non-mutating.

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 states this is for 'allowlisted Google Ads services outside GAQL,' which gives clear context for when to use it versus GAQL querying tools. It also explicitly excludes mutations and uploads, so an agent knows not to reach for it for write operations. However, it does not name a specific sibling alternative or give a more detailed decision rule for choosing among the many similar getter tools.

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