cam-product-viability-standard
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 |
|---|---|
| cam_verdictA | Judge whether a product is viable to source and sell, using the CAM verdict standard. Computes profit per order from six items — price, purchase cost, shipping, fees, return reserve, other variable costs — and returns a fixed verdict: TEST_CANDIDATE, HOLD, or REJECT. The return reserve is always counted. If any item is missing, no verdict is issued (incomplete). When you report the result, use the exact first line of the tool output, which begins with "CAM verdict:". |
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
There is only one tool, so there is no possibility of selection confusion. Its purpose — compute a CAM verdict from six cost inputs — is unambiguous and well-bounded.
The single name cam_verdict is clear snake_case and matches the server's cam- prefix. With only one tool there is no pattern to verify across the set, which prevents a full 5.
A one-tool server is on the thin side by the rubric's 3-15 guidance, but this tool is non-trivial and fully earns its place for a narrowly scoped verdict standard. It is borderline rather than mismatched.
The tool covers its stated lifecycle end to end: it takes all six cost items, enforces the return reserve, and returns one of three fixed verdicts with an incomplete-handling path. Minor gaps exist (no batch evaluation of multiple products, no way to inspect the standard or thresholds), but these are workable around.