Skip to main content
Glama

atlas_set_custom_eval_rubric_overrides

Idempotent

Override a custom evaluation model's inferred rubric (weights, dimension names, criteria) without re-inferring; replaces any earlier overrides. 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>",
      "overrides": "<overrides>"
    },
    "name": "atlas_set_custom_eval_rubric_overrides"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYesFrom atlas_list_custom_eval_models
overridesYesKeyed by dimension name (weights, criteria, ...)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields 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"
    • changedInput schema / properties / overrides / description
      Previous value: -"Override object — keys are dimension names, values are override configs (weights, criteria, etc.)"New value: +"Keyed by dimension name (weights, criteria, ...)"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, idempotent, non-destructive, closed-world write, so the bar is lower. The description still adds real value by disclosing replacement semantics ('replaces any earlier overrides') — i.e. prior overrides are discarded, which is what makes the idempotent hint meaningful — and by noting the call is 'Free'. It does not say what happens when a supplied dimension name is not present in the inferred rubric.

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?

A single front-loaded sentence with the verb and resource first, the differentiating clauses second, and cost last. No filler, no repetition of schema fields, and the trailing 'Free.' earns its place by flagging that no credits are consumed.

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?

For a two-parameter mutation with no output schema, the essentials are covered: what gets replaced and that no re-inference occurs. It falls short on validation behavior (unknown dimension names, malformed criteria) and on how an agent should verify the result afterwards, which the sibling atlas_get_custom_eval_rubric would address.

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?

Schema coverage is 100% (model_id points at atlas_list_custom_eval_models, overrides is documented as keyed by dimension name), so the schema already does the heavy lifting. The description adds modest meaning by naming the fields that overrides can carry and by establishing that the override set is applied wholesale rather than merged; it says nothing about partial vs. complete override objects.

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?

The description gives a specific verb plus resource ('Override a custom evaluation model's inferred rubric') and enumerates the affected fields (weights, dimension names, criteria). The clauses 'without re-inferring' and 'replaces any earlier overrides' implicitly separate it from the inference and add-override siblings, though no sibling is named outright.

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?

Usage is only implied: an agent can infer this is the tool for supplying an explicit rubric instead of letting the model infer one. There is no explicit when-to-use statement, no prerequisite that the model and its inferred rubric already exist, and no pointer to atlas_infer_custom_eval_rubric or atlas_clear_custom_eval_rubric_overrides as alternatives.

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