Search the Ad Library

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

Annotations already signal a safe, read-only, idempotent operation, so the description adds behavioral value by disclosing that spend and reach are null outside the EU and that this is expected rather than an error. It also clarifies the return scope (advertiser, copy, creative count, etc.), which helps the agent interpret results correctly.

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?

Three sentences, each earning its place: the action, the return content, and a critical data caveat. The most important behavior is front-loaded, and the paragraph stays compact despite covering several nuances.

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 tool has 7 well-documented optional parameters, an output schema, and safe read-only annotations, the description is complete enough. It covers selection-relevant scope, the null-data gotcha, and the returned fields, leaving only details that are already in the schema.

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 100% and each parameter already has a rich description, including the query/page_id trade-off and defaults. The description frames keyword vs. page_id as two modes but adds little meaning beyond what the schema already states, so the baseline of 3 is appropriate.

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?

States a specific verb ('Search') and a clear resource ('Meta's public Ad Library'), and distinguishes two invocation modes: keyword search or listing all ads for a page_id. The phrase 'list every ad from one advertiser by passing page_id' also differentiates it from sibling tools that fetch a single ad or advertiser list.

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 sets useful context: it works for ordinary commercial advertisers in any country, and it preempts the EU spend/reach caveat. The schema adds explicit routing guidance ('Use list_advertisers first if you only know the brand name'), but the description itself does not spell out when to prefer siblings like get_eu_transparency or get_ad. This is clear context with room for firmer exclusion guidance.

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