Find Meta Ads

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

Annotations already cover read-only/idempotent/open-world, but the description adds substantial non-structural context: coverage is not universal (EU vs political-only elsewhere, with coverage notes on every row), the caller must supply their own Meta app token or META_ACCESS_TOKEN, political data needs a verified identity, Apify credits are consumed, null impressions/spend mean 'not reported' rather than zero, and each call is a point-in-time read. That is exactly the behavioral burden the annotations cannot carry.

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?

It leads with purpose and return shape, then coverage caveats, then auth, then usage, then exclusions — a sensible priority order with essentially no filler sentences. It is dense and long, and a few clauses (e.g., restating the EU coverage rule) could be tightened, which keeps it from a 5.

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?

With 9 parameters, no required fields, no output schema, and a complex external API, the description carries everything an agent needs: what a row contains, the coverage trap that produces false negatives, token/credit prerequisites, idempotency via caching, and the point-in-time nature. Nothing material is missing.

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% with rich per-parameter descriptions, so the baseline is 3. The description still adds cross-cutting meaning over the schema: it explains that the row always reports total matches before the maxAds cap, that caching makes repeated runs free, and that ad_reached_countries is what determines whether coverage is universal or political-only.

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 first sentence gives a specific verb (search), a specific resource (Meta Ad Library / Facebook Graph API), and even the return shape (one flat row per ad with named fields), so an agent knows exactly what it gets back. It has no siblings to disambiguate against, so nothing is left for inference.

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?

It states the two legitimate uses ("check whether a company advertises... right now or to pull a creative history"), explains the monitoring pattern (call on a schedule and diff rows), and explicitly excludes organic posts and follower counts by naming the mappers that cover them. That is when-to-use, how-to-use repeatedly, and when-not-to-use in one place.

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