Skip to main content
Glama

Re-aggregate

reaggregate

Recompute an evaluation's total using a different aggregation method, formula, weights, gates, grades, or pass threshold, without re-running judges. Use it for what-if analysis and optional persistence.

Instructions

Recompute the total with a different aggregation (method, formula, weights via gates/grades/passThreshold) without re-running judges. Useful for what-if analysis.

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": {
      "evaluationId": "<evaluationId>",
      "aggregation": "<aggregation>"
    },
    "name": "reaggregate"
  }
}

Input Schema

NameRequiredDescriptionDefault
persistNo
aggregationYes
evaluationIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It usefully discloses that judges are not re-run (a cost/side-effect fact an agent could not infer), but says nothing about what 'persist' does, whether a recompute can overwrite the stored total, or what the call returns.

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

Conciseness4/5

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

Two tight sentences, front-loaded with the action and followed by the qualifying constraint. The parenthetical packing three field groups is dense but still readable; nothing is wasted.

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 tool with no annotations, no output schema, and an opaque nested object, the description covers the aggregation payload and the no-judge-recompute behavior but omits the write semantics of 'persist' and any indication of the returned shape. It is adequate rather than complete.

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 0% and 'aggregation' is an untyped additionalProperties object, so the description's parenthetical (method, formula, weights via gates/grades/passThreshold) is genuinely valuable in revealing what belongs inside it. However it leaves 'persist' and 'evaluationId' unaddressed and gives no valid values for 'method'.

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+resource: 'Recompute the total with a different aggregation.' The clause 'without re-running judges' implicitly distinguishes it from the heavier 'evaluate' sibling, so an agent can tell what class of operation this is. It stops short of naming the alternative tool outright.

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?

'Useful for what-if analysis' plus 'without re-running judges' gives a clear condition for choosing this over a full evaluate run. There is no explicit when-not guidance or named alternative, so it falls just short of a 5.

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