Skip to main content
Glama

decision_evaluate

Evaluates multimodal inputs—documents, media, code, or text—against multiple typed questions in parallel via Gemini Decisions API, returning calibrated answers and confidence scores.

Instructions

Evaluate multimodal state (Excel, Word, PPTX, PDF, media, code, text) against multiple typed questions in parallel using Gemini Decisions API.

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": {
      "state": "<state>",
      "questions": "<questions>"
    },
    "name": "decision_evaluate"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNogemini-decision-1
stateYes
api_keyNo
questionsYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions parallel evaluation via the Gemini Decisions API and multimodal support, but does not state whether the operation is read-only, how authentication via api_key works, whether calls incur cost, or what failure behavior looks like.

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?

The description is a single front-loaded sentence with no filler. It conveys the core action, input scope, and execution model efficiently.

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

Completeness2/5

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

This is a complex tool with four parameters, nested objects, no annotations, and no schema descriptions. While an output schema exists to cover return values, the description remains too thin on parameter semantics, authentication, and when to choose this tool over siblings.

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 description coverage is 0%, so the description must compensate for undocumented parameters. It meaningfully clarifies that 'state' accepts Excel, Word, PPTX, PDF, media, code, and text, and that 'questions' are typed and evaluated in parallel, but it omits the 'model' and 'api_key' parameters and does not explain the nested question structure.

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 states a specific verb and resource: evaluate multimodal state against multiple typed questions in parallel. It clearly identifies the operation and supported input types, but it does not distinguish this tool from sibling evaluators such as jev_evaluate or decision_choice.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus alternatives like decision_choice, decision_score, or jev_evaluate. The phrase 'in parallel' hints at batch-oriented use, but no exclusions, prerequisites, or alternative-selection rules are provided.

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