cashflow-mcp-server

Compare contract variants

cashflow_compare_contracts

Read-onlyIdempotent

Compare 2-5 contract variants side by side and rank them by NPV, IRR, or payback to choose between payment plans, terms, or pricing structures.

Instructions

Evaluate two to five named contract variants and rank them side by side.

Built for the question these models exist to answer: pay cash or finance, 24 months interest-free or 36 with interest, higher fixed fee or higher per-unit price, 3-year term or 5-year.

Args:

variants (array): 2 to 5 entries of { name, model }.
rank_by ('npv' | 'irr' | 'payback'): Which metric orders the result. Default 'npv'.
response_format ('markdown' | 'json'): Default 'markdown'.

Returns: variants[] ordered best first by the chosen metric, each with its headline metrics and financing cost, plus the name of the winner.

Ranking by IRR places variants without a reportable IRR last, because an absent IRR is not a low one.

Examples:

Use when: "Should we take the 24-month interest-free plan or pay cash?"
Use when: "Compare a 3-year and a 5-year term on the same contract."

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rank_by`	No	Metric that orders the result.	npv
`variants`	Yes	The variants to compare.
`response_format`	No	'markdown' for a readable report, 'json' for the full structured result. Structured data is returned either way in structuredContent.	markdown

Output Schema

TableJSON Schema

Name	Required	Description	Default
`winner`	Yes
`rankedBy`	Yes
`variants`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 22, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety behavior is covered. The description adds valuable behavioral details: variants are ordered best-first by the chosen metric, each entry includes headline metrics and financing cost, a winner is named, and IRR-less variants are ranked last because an absent IRR is not a low one. This goes well beyond the annotations.

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?

The description is well structured with clear sections: purpose, args, returns, ranking nuance, and examples. It front-loads the core purpose and uses the examples efficiently. The phrase 'Built for the question these models exist to answer' is slightly unnecessary but not harmful.

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?

For a complex tool with nested model objects and an output schema, this description is sufficiently complete. It covers input constraints (2–5 variants), ranking metric defaults, response formats, output shape, ranking behavior, and practical examples. The schema and output schema handle the remaining parameter and return-structure details.

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 100%, so the baseline is 3. The description restates the shape of variants and the defaults for rank_by and response_format, but it does not add meaningful semantic depth beyond what the input schema already provides.

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 and resource: 'Evaluate two to five named contract variants and rank them side by side.' It clearly differentiates this from sibling tools like cashflow_evaluate_contract by framing it specifically as a multi-variant comparison, and the examples reinforce the intended use cases.

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?

The description provides explicit 'Use when' examples, such as comparing 24-month interest-free versus 36-month with interest, and comparing 3-year versus 5-year terms. It does not name sibling tools or state when not to use this tool, but the context is clear enough for an agent to select it for comparison questions.

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

Deploy Server