agent-eval-gate
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| authorize_funds_transferA | Authorize a funds transfer only if a version-pinned OFAC SDN screen returned CLEAR and COMPLETED before the transfer executed. Returns a structured DENY (with the OFAC rule cite) or ALLOW verdict; every unsafe ordering DENYs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no potential for ambiguity or confusion between tools.
The single tool name 'authorize_funds_transfer' follows a clear verb_noun pattern, which is trivially consistent.
The server has only one tool, which is borderline appropriate. While it serves a specific purpose, the count is minimal and could be considered thin.
For a server named 'agent-eval-gate', a single tool for authorizing transfers seems incomplete, lacking broader evaluation or gatekeeping capabilities.