CareerProof MCP

atlas_create_custom_eval_model

Create a custom evaluation model (your own scoring rubric) for a hiring context. Returns its id (model_id). Then teach it with artifacts and build its rubric with atlas_infer_custom_eval_rubric. Free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "client_context_id": "<client_context_id>",
      "name": "<name>"
    },
    "name": "atlas_create_custom_eval_model"
  }
}

Input Schema

Name	Required	Description
`name`	Yes
`description`	No
`client_context_id`	Yes	From atlas_list_contexts

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 11, 2026
- changedInput schema / properties / client_context_id / description
```
Previous value: -"Client context ID from atlas_create_context or atlas_list_contexts"New value: +"From atlas_list_contexts"
```
- removedInput schema / properties / description / description
```
Removed value: -"Model description"
```
- removedInput schema / properties / name / description
```
Removed value: -"Model name"
```
First observedMar 30, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations establish this is a non-idempotent, non-destructive write with no external side effects; the description adds the key result (returns model_id) and cost information ("Free") that annotations cannot express. It does not cover whether names must be unique or what happens on duplicate creation, which matters for a non-idempotent create.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and its return value, followed by the next step and cost. Every element carries information an agent can act on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter creation tool with no output schema, the description supplies the return value (model_id) and the follow-up tool, which is the essential operational context. The remaining gap is guidance on naming the model and whether duplicate names are permitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description carries the burden of explaining the required "name" and optional "description" parameters, and it does neither. Only the meaning of "name" is weakly implied by the phrase "custom evaluation model", and nothing clarifies naming constraints beyond the schema's maxLength.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Create a custom evaluation model") and immediately clarifies the concept as "your own scoring rubric" for a hiring context. It also names the returned identifier and points at the sibling that continues the workflow, so an agent can separate it from create_context or the get/list/update siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit ordered workflow: create the model, then teach it with artifacts, then build the rubric with atlas_infer_custom_eval_rubric. It does not state exclusions (e.g., when to reuse an existing model via atlas_list_custom_eval_models instead), so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CareerProof MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?