Skip to main content
Glama
Life Admin MCP

Life Admin MCP

by NKC27

Add item

add_item

Start tracking a bill, renewal, subscription, warranty, policy, vehicle or document. Records only the facts you provide, flagging exact duplicate titles and full card numbers.

Instructions

Start tracking something: a bill, renewal, subscription, warranty, policy, vehicle or document. Use only facts the user gave you; leave out a due date or cost rather than guessing. Refuses an exact duplicate title (use update_item instead) and anything that looks like a full card number.

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": {
      "title": "<title>",
      "type": "<type>"
    },
    "name": "add_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
dueNoNext renewal, payment or expiry date as YYYY-MM-DD. Only a date the user gave you.
refNoPolicy, account or order reference; only the last four are kept
costNoCost per period as the user stated it (for income: the amount received). Never estimate.
tagsNoA few lowercase tags, e.g. ['car']
typeYesWhat kind of thing it is
notesNoAnything else worth keeping, in the user's words
titleYesShort, specific name, e.g. 'Car insurance' or 'Boiler warranty'
periodNoHow often it repeats (default one-off)
currencyNoThree-letter code, default GBP
providerNoWho it is with, e.g. 'Octopus Energy'
auto_renewsNoTrue if it renews or charges automatically unless stopped
remind_daysNoDays before due to start reminding (default 14)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare this is a non-destructive, non-read-only, non-idempotent write, so the description correctly does not restate the safety profile. It adds genuine behavioral detail beyond the annotations: it will refuse an exact duplicate title and rejects input that resembles a full card number, both of which an agent cannot infer from structured fields. It does not say what a successful call returns, which is a remaining gap.

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?

Three short sentences, front-loaded with what the tool does, then the data-fidelity rule, then the two rejection cases. No filler and nothing important buried at the end.

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 12-parameter creation tool with full schema coverage and existing annotations, the description covers purpose, input honesty requirements, and the refusal cases that would otherwise surprise an agent. The only material omission is the absence of any statement about what a successful call returns or how the created item is identified, which matters since there is no output schema.

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 schema already documents all 12 parameters including defaults (period one-off, currency GBP, remind_days 14) and the last-four-only truncation of ref. The description's 'use only facts the user gave you; leave out a due date or cost rather than guessing' reinforces the due and cost semantics but largely echoes what those schema entries already say. Baseline 3 applies.

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 gives a concrete verb-plus-resource framing ('Start tracking something') and enumerates the resource types it covers (bill, renewal, subscription, warranty, policy, vehicle, document), matching the type enum. It also distinguishes itself from update_item by name, so the agent can separate creating from editing without inspecting either schema.

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 states when to use this tool (capturing something new to track) and gives a clear when-not for the most likely confusion: an exact duplicate title should go to update_item instead. It does not cover other creation-adjacent paths (e.g. restoring a removed item via restore_item), but the guidance it does give is explicit and actionable.

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