Skip to main content
Glama
paystack-mcp

paystack-mcp

by si-essence

paystack_disputes

Destructive

List, fetch, export, update, and resolve Paystack disputes, attach evidence, and view related transactions with confirmation-gated write actions.

Instructions

paystack_disputes. Actions: list (read), fetch (read), transaction (read), export (read), update (write), evidence (write), resolve (write). Writes need confirm:true and PAYSTACK_ALLOW_WRITES=true. Money actions also need PAYSTACK_ALLOW_MONEY_MOVEMENT=true. Otherwise this is a preview and no request is sent. Amounts are positive integers in subunits.

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": {
      "action": "<action>"
    },
    "name": "paystack_disputes"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
toNo
fromNo
nextNo
pageNo
actionYes
statusNo
confirmNo
messageNo
perPageNo
previousNo
resolutionNo
use_cursorNo
transactionNo
customer_nameNo
refund_amountNo
customer_emailNo
customer_phoneNo
service_detailsNo
uploaded_filenameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true and non-idempotent, so the safety profile is partly covered; the description nonetheless adds real context beyond them. The dry-run/preview semantics (no request sent unless confirm and env flags are set) and the subunit convention for amounts are behavior facts not present in the schema. It still omits what a resolve/update actually destroys or overwrites and whether writes are reversible.

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 text is a tight, front-loaded block: action taxonomy first, then gating rules, then the amount convention — no filler and no repetition of schema details. The only waste is the leading name restatement ('paystack_disputes.') which duplicates the tool name.

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?

For a polymorphic tool with seven actions, 20 parameters, no output schema and destructive writes, the definition leaves major gaps: it never says which parameters are required or valid per action, what the resolve versus evidence versus update flows look like, or what a response contains. The preview explanation is valuable but not enough to make the definition complete at this complexity.

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

Parameters2/5

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

Schema description coverage is 0% across 20 parameters, so the description carries the full explanatory burden and largely does not meet it: only confirm and refund_amount get any clarification (gate flag; positive integers in subunits). Parameters such as resolution, transaction, customer_name/email/phone, service_details, uploaded_filename, use_cursor, page/perPage, from/to/next/previous, status and message are left entirely unexplained, and there is no mapping of which parameters belong to which action.

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 names the resource (Paystack disputes) and enumerates every action with a read/write tag, so an agent knows this tool lists, fetches, exports, updates, adds evidence to, and resolves disputes. It stops short of a sibling-level distinction (nothing points to paystack_refunds or paystack_transactions for adjacent money operations), which keeps it 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 Guidelines4/5

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

It gives explicit preconditions for the mutating actions: confirm:true plus PAYSTACK_ALLOW_WRITES=true, and PAYSTACK_ALLOW_MONEY_MOVEMENT=true for money actions, with the important fallback that without these the call is a preview and no request is sent. The read/write labels also route the agent among the seven actions. What is missing is guidance on when to reach for this tool versus a sibling such as paystack_refunds.

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