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

Annotations only say read-only/idempotent/open-world; the description adds genuinely new behavior: a hard cap of 3 pages per search, the cursor protocol (pass returned `next` as `after` with page+1), the shape of each item (ad text, start/stop dates, platforms, Meta-only spend and impression ranges), and the account-binding prerequisite for the Meta provider.

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?

Front-loaded with the core action plus the read-only marker, then requirements, then result shape, then pagination — a sensible order. It is information-dense but slightly over-packed with parentheticals, so it reads as a single long block rather than scannable segments.

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 an 8-parameter, output-schema-less search tool this covers provider selection, query semantics, required credentials, pagination limits and return fields — nearly everything an agent needs. The gaps are the undocumented `limit` parameter and no explicit indication of what happens when the cap of 3 pages is reached.

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?

With 0% schema description coverage the description has to carry the parameters, and it does well: it defines ads_transparency_provider's two values, text_query's accepted forms (brand, advertiser, keyword, domain), country as a two-letter code defaulting to TR, the ads_account_id/ads_account_uuid requirement and the page/after relationship. Only `limit` is left completely unexplained.

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+resource+domain: 'Competitor ad archive search' over Meta Ad Library and Google Ads Transparency Center, and names the providers by their API values. It is clearly distinguishable from sibling ad tools like list_ads_meta_posts or ads_insights_* because it queries external public ad archives rather than the user's own accounts.

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?

Gives concrete selection guidance between the two providers (META requires an ads_account_id or ads_account_uuid of a connected account, GOOGLE does not) and a clear exclusion: 'TikTok is not covered by either archive.' It stops short of naming sibling alternatives (e.g. list_ads_meta_posts) as the tool to use instead for owned-account ad data.

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