Single tool with basic schema and description. Schema is present with proper JSON Schema structure (type, properties, required array), but lacks critical depth. Description is minimal (54 chars) and does not explain WHEN to use the tool or what it returns. Parameters lack descriptions for 'sort' and 'offset' fields. No output schema documented. No error handling guidance. Naming follows verb_noun pattern (search_ads) which is correct, but the tool lacks the richness expected of production-grade definitions.
Search for ads on the DealX platform
Missing parameter descriptions for 'sort' and 'offset'. LLMs cannot infer what 'sort' values are valid (e.g., is '-created' the only option?) or what 'offset' semantics mean (1-indexed vs 0-indexed).
Tool description is 54 characters and lacks context. Does not explain WHEN to use search_ads vs other discovery tools, what the response structure is, or how pagination works. Baseline for A+ tools is 194 chars.
No output schema documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., ad IDs for follow-up actions) without knowing the response structure.
No error handling guidance. If a search returns zero results or the API fails, the tool provides no recovery hints (e.g., 'Try a broader query' or 'Check your API key').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
Missing 'query' parameter description. While the name is clear, the description should specify: required vs optional, min/max length, supported operators (if any), and examples of valid queries.