Skip to main content
Glama

decisionmatrix-mcp

by io.github.inity13

sensitivity_analysis

Test how robust the winner is to changes in criteria weights. Sweeps each criterion's weight +/- 'variation' (default 0.2 = 20%) over 'steps' (default 10) increments, recomputes the ranking, and reports a robustness score, which criteria are most likely to flip the result, and the flip points.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stepsNoNumber of weight steps per criterion (2-100).
methodNoweighted_sum
scoresYesScore matrix. Object form: {"Option A": {"Criterion 1": 8, ...}, ...}. Array form: [{"option":"Option A","scores":{...}}]. Or inline scores on each option object.
optionsYesNamed alternatives. Strings ["A","B"] or objects [{"name":"A","scores":{...}}].
criteriaYesWeighted criteria. Each: {name, weight (relative, >=0), direction: 'benefit' (higher better, default) | 'cost' (lower better)}.
variationNoFractional weight sweep, 0<v<=1. 0.2 = +/-20%.

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the transparency burden. It clearly discloses the algorithm (sweeping +/- variation in steps, recomputing ranking) and the kinds of outputs (robustness score, flippable criteria, flip points). It does not state side effects, but 'test' and 'recompute' imply non-mutating 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?

A single dense sentence delivers purpose, mechanism, defaults, and output summary without filler. Every phrase earns its place, and the most important action is front-loaded.

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?

The tool is complex (six params, nested objects, no output schema), but the description only lists result categories qualitatively and omits the output format, edge-case behavior, and any dependencies on prior calls. It is adequate for a basic understanding but leaves gaps in return-value details.

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?

Schema coverage is high (83%), giving a baseline of 3. The description adds value by explaining that variation and steps control the weight sweep range and increment count, and it mentions their defaults. Other parameters are well-covered by the schema, so no further compensation is needed.

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

Purpose5/5

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

The description opens with a specific verb ('Test') and a clear resource: robustness of the winner to criteria weight changes. It explains the sweeping mechanics and outputs, making it easily distinguishable from siblings like score_options and compare_two.

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 context that this follows a ranking decision is implied by 'the winner', but the description never explicitly says when to use sensitivity_analysis versus alternatives, nor provides exclusions. No alternative tools are mentioned, so guidance is implied rather than stated.

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

All decisionmatrix-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: compare_two is specifically for two-option head-to-head, create_decision is the main ranking tool with explanation, score_options returns the scored matrix without narrative, and sensitivity_analysis tests weight robustness. Health check and list_methods serve auxiliary but separate roles. No two tools are likely to be confused.

Naming Consistency4/5

Most tools follow a verb_noun pattern (create_decision, list_methods, score_options, compare_two), but sensitivity_analysis is a noun phrase without a verb, and compare_two uses a number instead of a noun. The snake_case style is consistent throughout, making the set readable overall.

Tool Count5/5

With 6 tools, the server is well-scoped for its decision-analysis purpose. Each tool covers a distinct aspect of the workflow: creation, pairwise comparison, scoring, sensitivity analysis, and method discovery. The count feels neither sparse nor bloated.

Completeness5/5

The tool set provides comprehensive coverage of multi-criteria decision making: creating a full decision, comparing exactly two options, scoring without the narrative, and testing robustness. Including list_methods for methodology details and health_check for server status rounds out the surface. No significant gaps are apparent for the stated domain.

Resources