Get Ad Insights

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds the behavioral constraint that one of the four IDs must be provided, which is useful but not deeply elaborated. No mention of rate limits, pagination, or response format beyond the schema.

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 well-organized, starting with the purpose and following with a clear bulleted list of arguments. There is no redundant wording, and the 'Provide one of' callout is concise and helpful.

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 read-only insights tool, the description covers the main selection logic but leaves gaps: it does not specify what happens if no ID is provided (contradicting the schema's zero required parameters), nor does it describe the output format or pagination. The response_format parameter exists in the schema but is not mentioned in the description, though it is documented there.

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 only 33%, leaving six parameters undocumented. The description compensates by explaining the ID parameters (e.g., 'All ads in campaign') and giving a date format for since/until. It also clarifies the constraint of providing exactly one ID. However, it omits response_format, which is documented only in the schema.

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 gets performance insights at the individual ad level, which is a specific verb and resource. The 'ad level' scope differentiates it from siblings like meta_get_campaign_insights and meta_get_adset_insights. It also lists the key parameters, reinforcing its purpose.

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 guidance on parameter selection ('Provide one of: ad_id, adset_id, campaign_id, or ad_account_id') but offers no guidance on when to use this tool versus other insights tools. It does not mention alternatives or conditions that would favor this tool, leaving the agent to infer from the name alone.

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