List ad groups

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds that budget is located here, which is a useful disclosure about what data is returned, and mentions the option to filter by campaign_id. However, it doesn't disclose pagination behavior (cursor/count) or the meaning of with_deleted, which are relevant to how the data is retrieved. Given the safety annotation, the additional context is modest but not deep.

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 sentences, front-loaded with the core purpose, and includes the key distinguishing fact about budget placement. No wasted words; every sentence adds value. This is a model of concise, effective documentation.

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 tool with 5 parameters, low schema coverage, and no output schema, the description is incomplete. It omits explanations for count, cursor, and with_deleted, and does not describe the return format or any pagination details. While readOnlyHint covers safety, the description does not provide sufficient guidance for an agent to call the tool correctly with all parameters or interpret the response.

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 only 20% (only account_id is documented). The description explicitly explains that campaign_id is an optional filter, which adds meaning for that parameter. However, it leaves count, cursor, and with_deleted unexplained. With low schema coverage, the description must compensate, but it only partially does, covering just one of the five parameters.

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 verb+resource: 'List line items (ad groups)' and specifies the fields returned (status, objective, bid). It also distinguishes itself from the sibling 'list_campaigns' by noting that budget lives here, not on the campaign, which differentiates the tool without ambiguity.

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 for when to use this tool: it lists ad groups and highlights that budget is stored on the line item, not the campaign. This implicitly signals to use this when budget info is needed, though it does not explicitly name alternates or exclusions. It gives enough context to choose correctly among siblings.

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