Descartes
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | API key for Exa to ground world doubts with real evidence. | |
| FIREWORKS_API_KEY | No | API key for Fireworks to enable panel of model families for doubt resolution. | |
| OPENROUTER_API_KEY | No | API key for OpenRouter as fallback when sampling is unavailable. | |
| DESCARTES_PANEL_SIZE | No | Maximum number of models in the panel for live path (optional). |
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 |
|---|---|
| doubtA | Doubt every decision in a plan, doubt the doubts, and answer each from
real evidence — codebase Args: prompt: the task / plan to harden. context: real evidence (paste relevant files, types, tests, notes) used to resolve code doubts without guessing. max_passes: convergence ceiling (clamped to 20). Returns: {passes_used, converged, plan, doubt_log, needs_user, engine, open_doubts} |
| groundB | Exa deep search -> cited, confidence-scored facts (used inside the loop). Low confidence is reported as UNKNOWN and never asserted. |
| verdictA | Gate a doubt() result. Proceed only if the plan converged with no open load-bearing doubt remaining; otherwise return the blocking questions. |
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 3 tools
Each tool serves a distinct role: doubt handles the iterative planning and doubt resolution, ground performs factual retrieval, and verdict gates the output. No overlap in functionality.
Names are single words but mix verb and noun forms ('ground' as verb, 'verdict' as noun) without a consistent pattern like verb_noun.
Three tools is minimal but well-scoped for the plan hardening domain, covering the main loop, evidence gathering, and output gating without apparent bloat.
The tool set covers the core workflow: iterative doubt resolution (doubt), external fact retrieval (ground), and a validation gate (verdict). Minor gaps like plan editing are absent but the core loop is complete.