Research ads

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

Annotations already declare readOnlyHint (safe) and openWorldHint (variable results). The description adds transparency about resource consumption ('Spends LLM tokens + ScrapeCreators credits') and explains it is a 'Claude tool-use loop', implying multiple API calls. No contradictions with annotations.

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?

Two-sentence description is concise, front-loaded with the core action, and contains no redundant information. Every sentence adds value.

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 an output schema present, the description does not need to detail return values. However, it lacks context on when to choose this over the many sibling search and competitor tools. It also omits potential timing/cost details (beyond a brief mention) that would help the agent manage expectations.

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 covers both parameters (query, brand) with descriptions. The description reinforces that query is a natural-language request and brand can be omitted to use saved brand. It also explains the output (summary + ads) which the schema does not, adding value beyond the schema.

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 clearly states it performs natural-language ad research across multiple platforms (Meta/Google/LinkedIn/TikTok) and returns a summary with found ads and their URLs. This distinguishes it from sibling search tools like search_meta_ads which focus on a single platform.

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?

No explicit guidance on when to use this tool versus alternative search tools (e.g., search_meta_ads for Meta-only queries, or pull_competitor_ads for competitor-specific research). The description implies broad cross-platform use but does not set expectations or provide exclusions.

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