Skip to main content
Glama

MoneyMatter

by io.github.letehaha
OverviewDiscussionsAdmin

update_tracker

Update the name, date range, spending limit, or rules (categories, tags, auto-add) of an existing tracker. Only passed fields change; limitAmount null removes the limit. With rules on, every update re-checks all transactions against them. Lines are managed with create_tracker_line, update_tracker_line and delete_tracker_line. Changing smart-tracking fields or dates rescans the tracker and fails while a scan is already queued or running. Returns the updated tracker record.

Input Schema

NameRequiredDescriptionDefault
nameNoNew tracker name
tagIdsNoReplace the rule tags
endDateNoNew end date (ISO 8601)
aiEnabledNoTurn smart tracking on or off. Owner only; enabling needs a description and a start date (already saved or passed here)
startDateNoNew start date (ISO 8601)
trackerIdYesID of the tracker to update
categoryIdsNoReplace the rule categories; parent IDs include their children
limitAmountNoNew spending limit as a decimal amount in the user's base currency (e.g. 500.00). Pass null to remove the limit
rulesCleanupNoRemove rule-added transactions that stop matching the rules
rulesEnabledNoAuto-add the user's transactions in the date range matching the rule categories or tags
aiDescriptionNoPlain-language description of what belongs in the tracker (max 500 chars). Owner only; null clears it
aiPreWindowDaysNoDays before startDate the AI also scans. One of 0, 14, 30, 60, 90, 180. Owner only

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / aiEnabled / description
      Previous value: -"Turn smart tracking on or off. Owner only; manual trackers only; enabling needs a description and a start date (already saved or passed here)"New value: +"Turn smart tracking on or off. Owner only; enabling needs a description and a start date (already saved or passed here)"
    • removedInput schema / properties / autoInclude
      Removed value: -{
-  "description": "Whether to auto-include transactions in the date range",
-  "type": "boolean"
-}
    • changedInput schema / properties / categoryIds / description
      Previous value: -"Replace the linked category IDs (only applies to category-type trackers)"New value: +"Replace the rule categories; parent IDs include their children"
    • addedInput schema / properties / rulesCleanup
      Added value: +{
+  "description": "Remove rule-added transactions that stop matching the rules",
+  "type": "boolean"
+}
    • addedInput schema / properties / rulesEnabled
      Added value: +{
+  "description": "Auto-add the user's transactions in the date range matching the rule categories or tags",
+  "type": "boolean"
+}
    • addedInput schema / properties / tagIds
      Added value: +{
+  "description": "Replace the rule tags",
+  "items": {
+    "format": "uuid",
+    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+    "type": "string"
+  },
+  "type": "array"
+}
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses partial-update semantics ('Only passed fields change'), that limitAmount null removes the limit, that every update re-checks all transactions when rules are on, and that date/smart-field changes trigger a rescan that can fail. It also states it returns the updated record. It omits permission requirements (owner-only) that appear only in schema descriptions, but the mutation and side-effect behavior is well covered.

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?

Front-loaded with the primary action and scoping, then terse sentences covering partial-update semantics, side effects, line-tool routing, and the rescan failure condition. Every sentence carries functional information; it is slightly dense but not padded.

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 mutation tool with no annotations and no output schema, the description covers the key operational risks (rescans, re-checks, failure while scanning) and states the return value. Permission details live in the schema, so an agent has enough to call this correctly; only per-field nuance depends on schema reading.

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 100%, so the baseline is 3; the description adds cross-parameter meaning beyond the schema by explaining that only supplied fields change and that null on limitAmount removes the limit rather than erroring. It does not restate individual parameter constraints (enum, owner-only), which the schema already handles, so it stays a modest value-add over baseline.

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?

States a specific verb (Update) and resource (existing tracker) and enumerates the updatable facets: name, date range, spending limit, rules. It also explicitly demarcates scope by naming create_tracker_line/update_tracker_line/delete_tracker_line as the tools for line management, so an agent can distinguish this from sibling tracker tools without reading schemas.

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?

Routes line editing to the three line-specific siblings and warns that changes to smart-tracking fields or dates fail while a scan is queued or running, which is genuine when/when-not guidance. It does not explicitly compare against create_tracker or archive_tracker, but the mutation scope and failure condition are clearly stated.

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

All MoneyMatter toolsInspect
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