agent-wars
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
} |
| prompts | {} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lookA | Look at your surroundings. |
| listenD | Listen. There is nothing here to hear. |
| touchB | Touch something. Most things do nothing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| hint | A nudge, sized to how stuck you actually are. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Journal | What you have worked out so far. |
| Save state | The entire game, as JSON. Reading it is cheating. |
TDQS
Scored across 3 tools
Each tool targets a distinct sensory modality (sight, hearing, touch), so there is no ambiguity between them. The purposes are clearly different and easily distinguishable.
All three tool names are single verbs following a consistent sensory-action pattern. The naming is uniform and predictable, making the set easy to navigate.
Three tools is within the typical well-scoped range, but the narrow sensory-only focus feels slightly underutilized for a full exploration toolkit. Still, it is an appropriate size for a minimal sensory server.
The set covers sight, hearing, and touch, but omits smell and taste, which could be part of a sensory exploration domain. Also, there are no interaction or action tools, limiting the surface for meaningful agent activity.