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

Beyond the annotations, it discloses quota mechanics (one read allowance per nonempty request), result bounds (account allowance, up to 20 ads), persistence to the user's Puley history, and a false-negative caveat that an access error or empty sample is not proof of no ads. This is genuinely additive context not present in readOnlyHint/openWorldHint. It does not state authentication or per-country filtering behaviour, so it stops short of a 5.

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 content is dense but every sentence contributes: platform routing, identity caveat, return contents, false-negative warning, quota/bounds, and the no-mutation statement. The only structural weakness is the mid-sentence line break and a slightly run-on flow that could be split into clearer clauses.

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 no output schema, the description usefully summarises what comes back (ad links, copy, advertiser IDs, destination links) and covers quota, bounds, and the read-only-in-spirit caveat. It remains incomplete for a 6-parameter open-world tool because limit, status, country, and platform values are never described.

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 0%, so the description must carry the burden, and it explains only 'query' and 'advertiser' semantically, plus an implicit platform split. It says nothing about 'limit', 'status', 'country' (including the 'ALL' default), or the accepted 'platform' values, leaving half the parameters undocumented anywhere.

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 opens with a specific verb and resource — searching the Meta Ad Library (Facebook/Instagram) or Google Ads Transparency — and names the two distinct advertiser-targeting modes. That is enough to separate it from neighbouring tools such as search_posts, google_results, or product_ad_pack without opening the schema.

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 gives concrete routing guidance per platform: for Meta, query searches keywords while advertiser targets a Page URL/id/name; for Google, the advertiser name, website or ID is used. It also cautions that a website keyword is not a verified Page identity, which steers correct input choice. What it lacks is explicit when-to-use/when-not guidance relative to siblings or named alternatives.

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