Skip to main content
Glama

rule_activity

Read-onlyIdempotent

Lists the mails a reply rule has processed, newest first, with status and skip or failure reasons, so you can verify the rule behaves as expected. Read-only, local, no mail text.

Instructions

List the mails a reply rule has looked at, newest first.

Returns, per mail: message_id, sender, status (for example 'sent',
'awaiting_approval', 'skipped', 'failed'), reason (why it was skipped or
failed, when there is one), request_id (the approval request of the
reply it prepared, when there is one) and ts (unix time). Use it to see
whether a rule is doing what the user expects. Read-only and local. The
mail text is not returned. Raises an error for a rule that does not
exist.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "rule_id": "<rule_id>"
    },
    "name": "rule_activity"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many of the most recent entries to return, from 1 to 200.
rule_idYesRule id exactly as returned by list_rules (for example 'rule_1a2b3c4d').

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.8

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, so 'Read-only and local' is largely redundant, but the description adds genuinely new behavior: it enumerates the returned fields and status values, states that mail text is withheld, and discloses that a nonexistent rule raises an error rather than returning empty.

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?

Purpose and ordering are front-loaded, then return fields, then intended use, then caveats. Every sentence carries information; the only near-waste is repeating 'read-only' from the annotations.

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?

Covers purpose, return shape, error behavior, and privacy constraint, and an output schema exists so return values need not be restated. Minor gaps remain: no mention of what a status of 'awaiting_approval' implies for follow-up, and no explicit statement that an empty list is a valid result for an existing rule with no activity.

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%, so rule_id format and the limit range/default are already documented structurally. The description only contributes the ordering semantics ('newest first') that make 'limit' meaningful, which is a marginal add-on — 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 and resource ('List the mails a reply rule has looked at') plus the ordering ('newest first'), which no sibling tool provides. An agent can distinguish this diagnostics view from list_rules or list_messages purely from the first line.

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?

Gives a clear intended use case ('see whether a rule is doing what the user expects') and a failure condition ('Raises an error for a rule that does not exist'). It stops short of naming when NOT to use it or pointing at an alternative tool for general message listing.

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