Best fit
Review function-calling tool definitions before exposing them to an agent.
Lint the function-calling tool definitions your agent exposes, so it picks the right tool instead of the wrong one or none.
Format: Agent skill, not a browser app. You need an AI agent that can load its instructions and use the required tools.
Package requirements: Agents that read the open SKILL.md format. Verify runtime and service requirements at the purchase or install destination.
You get: Findings on missing descriptions and types, overlapping tools, selection complexity and missing safeguards around sensitive operations.
Review the package licence at the destination.
Review the offer and access method at your chosen marketplace. Agensi provides connected-agent access, not a download. Buying a skill does not include an AI-agent subscription or setup service.
Point it at your tool-definition JSON or pipe it in. Read-only.
This is heuristic; the unsafe-tool rule is advisory. It is distinct from REST API tooling: this targets function-calling definitions.
Review function-calling tool definitions before exposing them to an agent.
Findings on missing descriptions and types, overlapping tools, selection complexity and missing safeguards around sensitive operations.
Do not treat a successful run as proof beyond the supplied files, declared scope, and evidence the skill actually checked.
Anyone building agents, MCP servers, or function-calling apps.
No. Read-only. It flags issues for you to fix.
Current price and purchase option are shown on Agensi. Use a supported agent connection on Agensi. Review the requirements above before getting started.
Get the Tool Schema Linter on Agensi