Skip to main content
Glama

atlas_infer_custom_eval_rubric

Build a custom evaluation model's rubric (dimensions and scoring criteria) from its artifacts. Answers directly in 30-60 s. 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": {
      "model_id": "<model_id>"
    },
    "name": "atlas_infer_custom_eval_rubric"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYesFrom atlas_list_custom_eval_models

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / model_id / description
      Previous value: -"Model ID from atlas_create_custom_eval_model or atlas_list_custom_eval_models"New value: +"From atlas_list_custom_eval_models"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing expected latency (30-60 s) and cost (free), which materially affects agent planning for a non-idempotent call. The main undisclosed behavior is whether an existing rubric is replaced or merged, which matters given idempotentHint=false and the presence of clear/set override siblings.

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?

Two sentences with zero filler, front-loading the action and scope before the latency and cost facts. Every clause carries actionable information for an agent deciding whether to invoke it.

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

Completeness3/5

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

Covers input (a model id) and roughly what comes back (dimensions and scoring criteria), which partly compensates for the absence of an output schema. It is not complete for a non-idempotent mutating tool: the effect on any pre-existing rubric and what to do next (get vs. set overrides) are unstated.

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

Parameters3/5

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

Only one parameter exists and the schema already documents it at 100% coverage, including its provenance (from atlas_list_custom_eval_models). The description adds no further parameter meaning, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb and resource: build a custom evaluation model's rubric, and parenthetically defines what a rubric contains (dimensions and scoring criteria). This clearly distinguishes a generative build action from retrieval siblings like atlas_get_custom_eval_rubric, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

The phrase "from its artifacts" implies a prerequisite (artifacts must already be attached to the model via the add/upload artifact tools) and the latency/cost notes help an agent decide between this and a cached retrieval. However, there is no explicit when-to-use/when-not guidance and no mention of how this relates to setting or clearing rubric overrides.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources