Decision Workspace
tool-arg-coerce vs agentvet vs agentcast
Side-by-side comparison of Rust crates
47
tool-arg-coerce
experimentalv0.1.0
Fix common type slips in LLM-generated tool arguments: string->int/float/bool, single-element array->scalar, null->default. Lossy and forgiving.
45
agentvet
experimentalv0.1.0
Validate LLM-generated tool args before execution. Throws a structured ToolArgError with LLM-friendly retry hints when the model hallucinates wrong types or missing fields.
44
agentcast
experimentalv0.1.0
Structured-output enforcer for LLM responses. Repair + validate + (optional) retry-with-LLM. BYO-LLM, BYO-schema.
Core Metrics
| tool-arg-coerce | agentvet | agentcast | |
|---|---|---|---|
| Health Score | 47 | 45 | 44 |
| Total Downloads | 18 | 32 | 17 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 0 | 0 |
| Releases | 1 | 1 | 1 |
| Last Updated | 58d ago | 65d ago | 64d ago |
| Age | 1m | 2m | 2m |
Health Breakdown
tool-arg-coerce
Maintenance
10
Quality
14
Community
6
Popularity
2
Documentation
15
agentvet
Maintenance
9
Quality
13
Community
6
Popularity
2
Documentation
15
agentcast
Maintenance
9
Quality
13
Community
6
Popularity
1
Documentation
15
Technical Details
| tool-arg-coerce | agentvet | agentcast | |
|---|---|---|---|
| Version | 0.1.0 | 0.1.0 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | MIT OR Apache-2.0 | MIT | MIT |
| Dependencies | 1 | 4 | 6 |
| Crate Size | 8KB | 11KB | 15KB |
| Features | 0 | 0 | 0 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.74 | 1.75 | 1.75 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •tool-arg-coerce leads with a health score of 47/100, but none of the options score above 80.
- •agentvet has the most downloads (32), suggesting wider adoption.