Skip to main content
Glama
Sign In
openai-decisions-mcp

openai-decisions-mcp

by semanticist21
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

decide

Read-only

Evaluate text, project files, images or PDF pages against your predicate, choice or score questions in one batch request, returning compact answers and coverage.

Instructions

Evaluate text, project files, images or PDF pages against caller-defined predicate, choice or score questions. Batch independent questions about shared evidence. Use paths instead of copying files. Returns compact answers and coverage; full=true includes all probabilities. Makes a paid OpenAI API request.

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": {
      "sources": "<sources>",
      "questions": "<questions>"
    },
    "name": "decide"
  }
}

Input Schema

NameRequiredDescriptionDefault
fullNo
sourcesYesPrefer a native JSON array. A JSON-encoded array string is also accepted for client compatibility; identical validation applies.
questionsYesPrefer a native JSON array. A JSON-encoded array string is also accepted for client compatibility; identical validation applies.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint, openWorldHint), and the description adds information not in them: the call issues "a paid OpenAI API request," which is a material cost disclosure. It also describes the return shape (compact answers and coverage, with full=true for all probabilities). It stops short of rate limits, auth requirements, or failure behavior.

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?

Four short sentences, each carrying distinct information: capability, batching, path usage, return format, and cost. The most decision-relevant capability statement is front-loaded and there is no filler.

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?

With no output schema, the description correctly steps in to describe the return value (compact answers plus coverage, full=true expands probabilities) and discloses the paid-call side effect. "Coverage" is left undefined and there is no guidance on partial failures or source-size limits, so it is strong but not exhaustive.

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

Parameters4/5

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

With 67% schema coverage the description meaningfully compensates: it explains that sources can be paths rather than copied file content, that questions come in three modes, and what full=true controls. This is real added semantics rather than restating the schema, though it does not explain the per-source fields like start_line/end_line or pdf pages/mode.

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 (Evaluate) and enumerates both the resource types (text, project files, images, PDF pages) and the question modes (predicate, choice, score). An agent can tell exactly what it does. It does not differentiate from the sibling evaluate_batch, which is the only thing keeping this from a 5.

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?

"Batch independent questions about shared evidence" and "Use paths instead of copying files" give genuine usage context, and "independent" implies a constraint. However, no exclusion criteria are stated and the sibling evaluate_batch is never named, so the agent has no explicit signal for choosing between the two.

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

Deploy Server

Other Tools