Skip to main content
Glama
Sign In
icloud-mcp

icloud-mcp

by adamzaidi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

update_digest_state

Records email digest run results by merging processed UIDs, updating lastRun, refreshing pending actions, and accumulating per-sender skip counts for future runs.

Instructions

Update the digest state after a run. Merges new processed UIDs into the existing list, updates lastRun, replaces pendingActions, and accumulates per-sender skip counts.

Input Schema

NameRequiredDescriptionDefault
lastRunNoISO timestamp of this run
skipCountsNoMap of sender address to skip count increment for this run, e.g. { "news@example.com": 3 }. Accumulated across runs for smart unsubscribe.
processedUidsNoEmail UIDs processed in this run — merged with existing and capped at 5000
seenRemindersNoSnapshot of all active reminders in the "claude" list at end of this run — used next run to detect which ones the user deleted. Each: { id, title, notes? }.
pendingActionsNoFull replacement list of pending action items to track across runs (deadlines, waiting-for-reply, etc.). Each item: { type, subject, to/from, dueDate?, notes? }
dismissedRemindersNoFull replacement list of reminders the user has deleted from the "claude" list (treated as "not interested"). Each: { title, notes?, dismissedAt (ISO) }. Entries older than 30 days are pruned automatically. Capped at 500.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.8.0
    • addedInput schema / properties / dismissedReminders
      Added value: +{
+  "description": "Full replacement list of reminders the user has deleted from the \"claude\" list (treated as \"not interested\"). Each: { title, notes?, dismissedAt (ISO) }. Entries older than 30 days are pruned automatically. Capped at 500.",
+  "type": "array"
+}
    • addedInput schema / properties / seenReminders
      Added value: +{
+  "description": "Snapshot of all active reminders in the \"claude\" list at end of this run — used next run to detect which ones the user deleted. Each: { id, title, notes? }.",
+  "type": "array"
+}
    • changedInput schema / properties / skipCounts / description
      Previous value: -"Map of sender address to skip count increment for this run, e.g. { \"bestbuy@email.bestbuy.com\": 3 }. Accumulated across runs for smart unsubscribe."New value: +"Map of sender address to skip count increment for this run, e.g. { \"news@example.com\": 3 }. Accumulated across runs for smart unsubscribe."
  2. First observedv2.5.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose useful mutation semantics (merge vs. full replacement per field), but much of this echoes the schema descriptions and it says nothing about permissions, idempotency, or failure behavior.

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?

A single front-loaded sentence that leads with the action and then lists the state changes compactly. No filler, though the list form is close to restating field names already in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter, nested-object, stateful mutation with no annotations or output schema, the description is adequate but thin: it omits the state model context (where the digest state lives, interaction with get_digest_state) and return behavior. The rich input schema compensates somewhat.

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 coverage is 100% with detailed per-parameter descriptions, so the baseline is 3. The description names four of the six parameters (processedUids, lastRun, pendingActions, skipCounts) but adds no syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Update) and resource (digest state) with the trigger condition 'after a run', and enumerates the fields it mutates. An agent can tell this is the write counterpart to get_digest_state, though the sibling is not named explicitly.

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

Usage Guidelines3/5

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

'after a run' implies when this should be called, but there is no explicit when-not, no mention of get_digest_state as the read alternative, and no stated prerequisites for calling it. Usage is inferable rather than guided.

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