testgen-eval
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_test_suiteA | Generate a structured test suite (functional, negative, boundary, security, usability cases) from a requirement or user story, using the testgen tool. Requires |
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
Only one tool exists, so there is no risk of confusion between tools. The agent will correctly select generate_test_suite for its intended purpose.
The single tool name 'generate_test_suite' follows a clear verb_noun pattern, which is a common and predictable convention. Consistency is not an issue with only one tool.
The server has only one tool, which is on the lower end of the acceptable range. While it might be sufficient for a very focused purpose (generating test suites), the scope feels thin compared to typical servers in this domain.
The tool provides a single operation for test suite generation. Missing are related operations like listing, updating, or exporting suites, but for a narrowly scoped 'eval' server, it may be acceptable. However, obvious gaps exist for a full test management workflow.