Skip to main content
Glama
ignaciohermosillacornejo

Copilot Money MCP

by ignaciohermosillacornejo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

get_recurring_transactions

Read-only

Identify recurring and subscription charges by combining merchant pattern analysis with user-confirmed Copilot subscriptions to return frequency, confidence, and next expected date.

Instructions

Identify recurring/subscription charges. Combines two data sources: (1) Pattern analysis - finds transactions from same merchant with similar amounts, returns estimated frequency, confidence score, and next expected date. (2) Copilot's native subscription tracking - returns user-confirmed subscriptions stored in the app. Both sources are included by default for comprehensive coverage. Rows in the pattern-analysis recurring array are terse by default: merchant, normalized_merchant, occurrences, average_amount, total_amount, frequency, confidence, category_name, last_date, next_expected_date. That excludes the matched transactions array (already reachable via get_transactions) and confidence_reason (prose explaining the score) — see fields for how to get either back.

Input Schema

NameRequiredDescriptionDefault
nameNoFilter by name (case-insensitive partial match). When filtering, returns detailed view with additional fields like min_amount, max_amount, match_string, account info, and transaction history.
fieldsNoReturn only these fields per detected recurring merchant. Default when omitted omits two expensive fields: `transactions` (the matched date/amount pairs, ~29% of a row) and `confidence_reason` (prose explaining the confidence score, ~15%). `confidence` itself is always in the default. Request the rest with fields: ["default", "transactions", "confidence_reason"], or "all" / "*" for full rows. Unknown names are omitted and reported via _field_warning.
periodNoPeriod to analyze (default: last_90_days). Options: this_month, last_month, last_7_days, last_30_days, last_90_days, ytd, this_year, last_year
end_dateNoEnd date (YYYY-MM-DD)
start_dateNoStart date (YYYY-MM-DD)
recurring_idNoFilter by exact recurring ID. When filtering, returns detailed view with additional fields like min_amount, max_amount, match_string, account info, and transaction history.
min_occurrencesNoMinimum number of occurrences to qualify as recurring (default: 2)
include_copilot_subscriptionsNoInclude Copilot's native subscription tracking data (default: true). Returns copilot_subscriptions array with user-confirmed subscriptions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.0.0
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Return only these fields per detected recurring merchant. Default when omitted omits two expensive fields: `transactions` (the matched date/amount pairs, ~29% of a row) and `confidence_reason` (prose explaining the confidence score, ~15%). `confidence` itself is always in the default. Request the rest with fields: [\"default\", \"transactions\", \"confidence_reason\"], or \"all\" / \"*\" for full rows. Unknown names are omitted and reported via _field_warning.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observedv2.0.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint, so the heavy lifting is on the description — and it delivers: default rows are a projection that omits two named expensive fields with rough payload shares, and it discloses the _field_warning mechanism for unknown names. It also notes that filtering by name/recurring_id switches to a 'detailed view'. Missing any guidance on result-set size or how many merchants a broad period can return, so not a 5.

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-loads the purpose and the source split before the payload detail, which is the right ordering. The `fields`/default-projection exposition is somewhat redundant with the schema's own description of the same parameter, costing a few lines of duplicated content.

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?

No output schema exists, so the description properly enumerates the default row fields and explains what is excluded — enough for an agent to know what it will get back. The shape of the copilot_subscriptions rows and the size of the combined payload under a broad period are left unspecified, but the core contract is covered for a 0-required-param read tool.

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 every parameter including the fields projection language and the period enum values. The description largely restates the `fields` default behavior that the schema also explains, adding emphasis rather than new meaning. 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?

States a specific verb+resource ('Identify recurring/subscription charges') and immediately decomposes the tool into two named data sources with distinct semantics (pattern analysis vs. user-confirmed Copilot subscriptions). It also names the sibling that already owns the matched transaction data (get_transactions), so an agent can tell it apart from the other read tools in the set.

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?

Explicitly states both sources are included by default for 'comprehensive coverage' and points to get_transactions as the route for matched transaction detail, which is real routing guidance. It stops short of saying when to prefer one source over the other or when to disable include_copilot_subscriptions, so it does not reach full when/when-not coverage.

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

Deploy Server

Other Tools