Skip to main content
Glama
googlarz

Proton Mail Bridge MCP

by googlarz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

get_follow_up_candidates

Read-only

Find email threads overdue for follow-up by age and pending-on state, surfacing sent messages without replies or stale inbound conversations.

Instructions

Return threads that appear overdue for follow-up based on age and pending-on state. Use when looking for outbound messages you sent that haven't received a reply, or to surface stale inbound threads. Prefer get_actionable_threads for threads where someone is currently waiting on you.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum candidate threads to return.
offsetNoSkip this many candidates (use nextOffset from the previous response to page).
pendingOnNoWhich side the candidate thread should be waiting on.you
syncBeforeNoRefresh the local mailbox index from IMAP before selecting candidates.
minAgeHoursNoMinimum thread age in hours.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.1.43
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Skip this many candidates (use nextOffset from the previous response to page).",
+  "type": "number"
+}
  2. Addedv1.13.11
  3. Removedv1.13.11
  4. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

The readOnlyHint annotation already establishes the safety profile, and the description adds the selection heuristic (age + pending-on state) and clarifies the non-overlapping scope with get_actionable_threads. It does not mention the potential IMAP refresh side effect of syncBefore or the response shape, but the added semantic context is meaningful.

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?

Three front-loaded sentences with zero filler: criteria first, then use cases, then the sibling preference rule. Every sentence earns its place.

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 read-only query tool with fully documented parameters, the description covers what the tool returns in kind ('threads'), when to reach for it, and when not to. It does not hint at the fields or paging metadata of the result, which is a minor gap given there is no output schema.

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 limit, offset, pendingOn, syncBefore, and minAgeHours. The description echoes the age and pending-on concepts but adds no format, default, or paging detail beyond the schema, so the 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 (Return) and resource (threads) plus the selection criteria (overdue for follow-up by age and pending-on state). It contrasts itself against get_actionable_threads by name, so an agent can distinguish the two candidates tools without reading either schema.

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 explicit when-to-use contexts (outbound messages with no reply, stale inbound threads) and an explicit alternative-plus-condition: 'Prefer get_actionable_threads for threads where someone is currently waiting on you.' Nothing is left to inference.

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