Paidnice

Update contact persons

update_contact_persons

DestructiveIdempotent

Replaces the full set of persons on a contact. Any existing person left out of the list is removed, so send every person to keep. The change is pushed to the accounting system and the contact is then re-synced. Exactly one person must be marked as primary. The primary person is imported, while additional persons may be local depending on accounting-system rules.

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": {
      "organisationId": "<organisationId>",
      "id": "<id>",
      "persons": "<persons>"
    },
    "name": "update_contact_persons"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`persons`	Yes
`organisationId`	Yes	Id of the organisation to act on, from list_organisations

Output Schema

Name	Required	Description	Default
`id`	Yes
`name`	Yes
`status`	Yes
`groupId`	Yes
`groupTitle`	Yes
`smsOptedOut`	Yes
`accountNumber`	No
`contactPersons`	Yes
`accountingSystemId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the destructiveHint/idempotentHint annotations, the description discloses the exact deletion semantics (omitted persons are removed), a downstream side effect (push to the accounting system plus re-sync), and a validation invariant (exactly one primary). That is real operational context an agent could not infer from structured fields.

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, front-loaded with the destructive replacement behavior before the finer constraints. Every sentence carries distinct information — omission semantics, side effects, primary rule, source-type rule — with no restatement of the name or title.

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

Completeness5/5

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

For a destructive, side-effecting mutation the description covers what gets destroyed, what happens downstream, and the validation rule on the payload; the output schema handles return values, so nothing an agent needs to call it safely is missing.

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 only 33%, with the complex `persons` array effectively undocumented, and the description compensates well: it explains the array is a complete replacement set, that exactly one entry must carry isPrimary, and how sourceType interacts with accounting-system rules. The top-level contact `id` is only implied ("on a contact"), which is the one remaining gap.

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?

"Replaces the full set of persons on a contact" names a specific verb (replace) and resource (contact's persons), and the full-replacement framing immediately distinguishes it from any additive or single-field edit. No sibling tool does a comparable write, so no sibling disambiguation is required.

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?

It gives the operative usage rule — "send every person to keep" — which tells the agent how to construct a correct call, and implies a read-first pattern (call get_contact before replacing). However, it never states when to reach for this tool versus other write paths or what preconditions (permissions, organisation scope) must hold.

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

All Paidnice tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?