get_recommendations

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

Beyond the annotations (readOnlyHint, destructiveHint), the description adds valuable context: it flags that budget-increase recommendations can be self-serving and highlights high-impact suggestions. This goes beyond basic safety traits to disclose potential bias.

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 efficiently structured in two paragraphs: first explaining what the tool does, then detailing parameters. It is reasonably concise, though slightly verbose in the parameter examples; still under 100 words and informative.

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?

Given the presence of an output schema, the description focuses on purpose, parameters, and behavioral context, which is sufficient. It covers the key aspects needed for an agent to use the tool correctly, though it could briefly mention the output schema or pagination if applicable.

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 description coverage, the description explains the parameters with examples for recommendation_types and clarifies behavior (empty = all types). It adds meaning beyond the raw schema, though customer_id is not described in detail.

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 retrieves Google's auto-generated recommendations with estimated impact, specifying the returned information (type, campaign/ad group, metrics, improvement). This distinguishes it effectively from sibling tools like confirm_and_apply, which apply recommendations.

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 use (retrieving recommendations with optional filters) and offers behavioral insight about self-serving budget-increase recommendations. However, it does not explicitly state when not to use this tool versus alternatives, though the read-only nature is implied.

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