agent-gpu-pool
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pool_overviewB | Show worker capacities separately and durable job counts. |
| list_workersA | List normalized worker capabilities without credential profiles. |
| sync_quotasB | Refresh authoritative provider quotas; unknown is not zero. |
| submit_jobC | Persist an experiment and return its job ID quickly; existing project policy controls dispatch. |
| get_jobC | Recover durable job state across agent sessions and broker restarts. |
| list_jobsC | List persistent jobs with pagination. |
| cancel_jobB | Request cancellation; status changes only when confirmed by the worker. |
| get_job_logsC | Bounded logs; offset counts backwards from the end of the available log window. |
| list_ready_resultsB | Discover finalized results from earlier sessions; check status before interpreting. |
| list_artifactsB | Return canonical paths, sizes, and hashes before reading content. |
| fetch_artifactC | Verify artifact hash and return its local path; content requires explicit true and is bounded. |
| record_experiment_resultD | Attach scientific interpretation separately from immutable infrastructure artifacts. |
| get_project_runsB | Return runs and recorded conclusions for a project. |
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 13 tools
The tools separate into clear functional areas: job lifecycle, artifacts/results, and pool/quota administration. Slight overlap exists among list_jobs, list_ready_results, and get_project_runs, where run/result/job terminology could cause misselection, but the descriptions clarify the intended use.
Almost every tool uses a verb_noun snake_case pattern such as submit_job, list_jobs, cancel_job, and fetch_artifact. pool_overview breaks the pattern as noun_noun, so the convention is consistent but not perfectly uniform.
Thirteen tools is a well-scoped size for a GPU pool and experiment management server. Each tool covers a distinct workflow step with no obvious redundant entries.
The set covers the core experiment lifecycle: submit, list, get, cancel, logs, artifacts, and recorded results, along with worker and quota visibility. Minor conveniences such as a dedicated quota getter or result update tool are absent, but agents can accomplish the intended workflows with the current surface.