Skip to main content
Glama
erayendes

Heimdall App Store Connect MCP

by erayendes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

finance_reports__list

Read-onlyIdempotent

Retrieve monthly financial reports from Apple App Store Connect, showing actual payments by region and currency. Filter by vendor, region, report type, date, and parse gzipped data into structured rows.

Instructions

Download the monthly financial report — what Apple actually paid, by region and currency, for a fiscal period. This is the money report, as opposed to units sold. Needs ASC_VENDOR_NUMBER and a Finance role on the API key. [GET /v1/financeReports] Set parse=true to receive decoded rows instead of the raw gzipped blob.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parseNoWhen true, gunzip and decode the TSV payload into structured rows ({ headers, rows, totalRows, truncated }) instead of returning the raw base64 blob. Defaults to false — unparsed, byte-for-byte identical to the raw response.
max_rowsNoMaximum number of data rows to include when parse=true (default 200, hard cap 1000). Ignored when parse is not true. Use truncated/totalRows in the response to tell whether more rows exist.
next_urlNoAbsolute links.next URL from a previous response.
filter_regionCodeYesfilter by attribute 'regionCode'
filter_reportDateYesfilter by attribute 'reportDate'
filter_reportTypeYesfilter by attribute 'reportType'
filter_vendorNumberYesfilter by attribute 'vendorNumber'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.0.0
    • addedInput schema / properties / max_rows
      Added value: +{
+  "description": "Maximum number of data rows to include when parse=true (default 200, hard cap 1000). Ignored when parse is not true. Use truncated/totalRows in the response to tell whether more rows exist.",
+  "type": "number"
+}
    • changedInput schema / properties / next_url / description
      Previous value: -"Absolute `links.next` URL from a previous response, to fetch the next page. When set, all other parameters are ignored."New value: +"Absolute links.next URL from a previous response."
    • addedInput schema / properties / parse
      Added value: +{
+  "description": "When true, gunzip and decode the TSV payload into structured rows ({ headers, rows, totalRows, truncated }) instead of returning the raw base64 blob. Defaults to false — unparsed, byte-for-byte identical to the raw response.",
+  "type": "boolean"
+}
  2. First observedv1.3.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description does not contradict them. It adds valuable context beyond those annotations: authentication requirements (vendor number + Finance role), the HTTP endpoint, and the critical default behavior that the raw response is a gzipped blob unless parse=true. It does not mention rate limits or pagination details, but those are partially covered by the next_url parameter.

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 description is compact and front-loaded: purpose first, differentiation second, then requirements and format behavior. Every sentence earns its place. It loses one point because the raw '[GET /v1/financeReports]' endpoint string is redundant for an agent selecting a tool, and the parse=true guidance partially duplicates the schema's parameter description.

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?

With no output schema, the description must disclose return behavior, and it does: raw gzipped blob by default, decoded rows with parse=true. It covers prerequisites, scope (region, currency, fiscal period), and the parse/max_rows/next_url mechanics are in the schema. Gaps are minor for a read tool: no mention of pagination flow, no format guidance for filter values (dates, region codes), and no explicit note that all four filters are required.

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 carries the parameter-documentation burden and the baseline is 3. The description adds marginal value by mapping ASC_VENDOR_NUMBER to the vendorNumber filter and hinting at parse=true, but those points are already well explained in the schema (e.g., parse's description covers gunzip, TSV decoding, and the response shape). Filter value formats for regionCode and reportDate are not elaborated anywhere.

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 opens with a specific verb + resource ('Download the monthly financial report') and defines what the content is: 'what Apple actually paid, by region and currency, for a fiscal period.' It proactively differentiates from the units-sold sibling ('This is the money report, as opposed to units sold'), which distinguishes it from sales_reports__list without any ambiguity.

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?

The description gives clear when-to-use context: it is the financial/money report rather than units sold, and it states explicit prerequisites ('Needs ASC_VENDOR_NUMBER and a Finance role on the API key') plus a format-selection hint (parse=true for decoded rows). It does not name the sibling tool sales_reports__list explicitly, so the exclusion is implied rather than fully explicit.

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