← Back to leaderboard
Plaid API
71
C
Plaid is the closest to a passing grade in this analysis — semantics, intent, and pagination all score 100. The spec is well-organized and operations are clearly named. But the gaps are sharp: zero documented error responses, and 74% of parameters lack descriptions. For a financial API, this matters: agents need to know what "ACCOUNT_NOT_AUTHORIZED" means vs. "ITEM_LOGIN_REQUIRED" to recover gracefully.
Category breakdown
Examples60
Semantics100
Intent100
Error Handling0
Parameters29
Pagination100
Key findings
- 2,107 of 2,254 schemas lack examples
- No error responses documented across any operation
- 960 of 1,296 parameters lack descriptions
- Semantics, intent, and pagination are exemplary — closest to a passing spec
What Plaid should fix
- Document error responses across all operations. For financial APIs, error specificity is the difference between a recoverable retry and a stalled user flow.
- Add descriptions to the 960 undescribed parameters. Plaid's domain terms (`access_token`, `cursor`, `count`) all have specific meanings that aren't obvious.
- Add examples to the 2,107 schemas missing them. Most of these are nested response objects where examples teach structure faster than reading schemas.
How does your API score?
Run AgenticScore on your own OpenAPI spec — find issues before LLMs do.
npx agenticscore score ./openapi.yaml
Get API Key →