search_linkedin_ads

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

Annotations already provide readOnlyHint=true, and the description adds useful behavioral context: it lists the returned fields (headline, description, CTA, destination URL, targeting, impressions, media URLs) and notes media URLs are meant for downstream analysis. This goes beyond the annotation, but it doesn't address pagination behavior, result ordering, or potential incompleteness of the Ad Library data.

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 five sentences, each adding distinct value: purpose, search methods, filter support, returned fields, and cross-tool directive. There is no filler or redundant phrasing, and the most critical information is front-loaded in the first sentence.

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 no output schema and sparse annotations, the description covers the essential return fields and provides clear pointers for further analysis. However, it omits pagination (pagination_token) and the meaning of `limit`, which are relevant for handling large result sets. A fully complete description would mention these to help agents use the tool effectively at scale.

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?

The input schema has no per-parameter descriptions (0% coverage), so the description must compensate. It explains company, keyword, company_id, countries, and date-range filters, but leaves `limit` and `pagination_token` entirely unexplained. It also does not specify date or country formats, so the parameter guidance is helpful but incomplete.

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 'Search LinkedIn's Ad Library for the ads a company is running,' which precisely identifies the verb (search), resource (Ad Library), and scope (ads of a company). It distinguishes itself from siblings by explicitly directing visual analysis to analyze_ad_image/analyze_ad_video, making its own search-and-return purpose clear.

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 clearly states multiple search strategies (by company name, keyword, or LinkedIn company ID) and even highlights company_id as 'most precise.' It explicitly instructs using analyze_ad_image or analyze_ad_video for visual analysis, which serves as a when-not-to-use this tool guidance. However, it does not mention when to use get_linkedin_ad_details compared to this search tool.

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