release-guard-mcp

Overview Schema Source Related Servers Discussions Admin

Audit App Store Server Notification delivery

reconcile_server_notifications

Read-onlyIdempotent

Report undelivered App Store Server Notifications (V2) using Apple's notification history. See counts by day, type, and failure reason to check for missed subscription webhook events.

Instructions

Report App Store Server Notifications (V2) that Apple could not deliver to your server, using Apple's notification history: counts by day, by notification type and by failure reason (TIMED_OUT, UNSUCCESSFUL_HTTP_RESPONSE_CODE, ...), with samples. Use for 'did our subscription webhook miss any Apple notifications?', 'check ASSN delivery for the last 7 days'. Report only: it never replays or changes anything. Needs an In-App Purchase key.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No	Look-back window in days (production keeps 180, sandbox 30).
`scope`	No	failures_only (fast) asks Apple only for failed or retrying sends; all scans every notification and adds a delivery rate.	failures_only
`max_pages`	No	Cap on 20-record pages to fetch.
`environment`	No	App Store Server API environment.	production

Output Schema

TableJSON Schema

Name	Required	Description
`end`	Yes
`pages`	Yes
`scope`	Yes	all: every notification in the window; failures_only: Apple's onlyFailures filter.
`start`	Yes
`by_day`	Yes
`by_type`	Yes	Undelivered count per notificationType.
`samples`	No
`scanned`	Yes
`delivered`	Yes
`next_step`	Yes
`truncated`	Yes	True if max_pages stopped the scan early.
`environment`	Yes
`undelivered`	Yes
`window_days`	Yes
`delivery_rate`	No	delivered / scanned, when scope is 'all'.
`replay_performed`	No	Always false: this tool only reports.
`by_failure_reason`	Yes	Undelivered count per last sendAttemptResult.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 29, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare read-only, non-destructive, idempotent, open-world behavior; the description adds required auth ('Needs an In-App Purchase key') and emphasizes that the tool never replays or changes anything. It also discloses the data source and returned breakdowns, going beyond the safety hints.

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?

Front-loaded with the reporting purpose, then usage examples, a no-side-effect guarantee, and auth needs. Every sentence earns its place with no redundant filler.

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?

With full schema coverage, rich annotations, and an output schema, the description only needs to cover purpose, usage, auth, and side-effect profile—all present and clear. Nothing material for correct invocation is missing.

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 four input parameters are fully documented in the schema. The description does not add syntax or meaning for days, scope, max_pages, or environment beyond what the schema already provides; baseline 3 is appropriate.

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 ('Report') and resource ('App Store Server Notifications (V2) that Apple could not deliver'), including the data source and breakdown dimensions. The sibling tools cover builds, versions, submissions, and release notes, so this audit tool is clearly distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two explicit trigger questions ('did our subscription webhook miss any Apple notifications?', 'check ASSN delivery for the last 7 days') and a when-not constraint ('Report only: it never replays or changes anything'). No sibling alternative exists for this audit purpose, so no further routing is needed.

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

Deploy Server