// agent-native
Tool Schema Linter
Lint the function-calling tool definitions your agent exposes, so it picks the right tool instead of the wrong one or none.
What it flags
- Tools or parameters with no description.
- Parameters with no type.
- Overlapping or near-duplicate tools.
- Too many tools for reliable selection.
- An unsafe tool exposed without a guard.
- Schema inconsistencies and unbounded free-form parameters.
How to run
Point it at your tool-definition JSON or pipe it in. Read-only.
Good to know
This is heuristic; the unsafe-tool rule is advisory. It is distinct from REST API tooling: this targets function-calling definitions.
Questions
Who is this for?
Anyone building agents, MCP servers, or function-calling apps.
Does it change anything?
No. Read-only. It flags issues for you to fix.
Help your agent pick the right tool.
Current price and purchase option are shown on Agensi. Instant download. Works with any agent that reads SKILL.md.
Get the Tool Schema Linter on Agensi