Skip to main content
Glama
loomiomcp
by soil-dev

get_user_activity

Read-onlyIdempotent

Retrieve a Loomio user's participation across selected groups, including monthly counts, per-group totals, and sample events for a date range.

Instructions

One person's participation across groups: 1 call per group + 1. Required user_id (from list_memberships or a participation row) and group_ids. Returns counts, by_group, sample_events (newest items with urls, not a full list). MONTH-GRAINED: since / until widen to whole months; anonymous polls never count; a vote counts in the month its counted stance row was created.

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": {
      "user_id": "<user_id>",
      "group_ids": "<group_ids>"
    },
    "name": "get_user_activity"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoISO-8601 start, rounded down to its month. Default: all history.
untilNoISO-8601 end (exclusive), rounded out to a whole month. Default: now.
user_idYesLoomio user id.
group_idsYesGroup ids (1-50); 1 call each.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.0.17
    • addedInput schema / properties / since / maxLength
      Added value: +64
    • addedInput schema / properties / until / maxLength
      Added value: +64
  2. Changed4 schema fields changedv0.0.13
    • changedInput schema / properties / group_ids / description
      Previous value: -"Groups to scan. Required — pass the result of `list_groups` (or a subset of it) to make the cost explicit. ~1 outbound HTTP request per discussion in scope, plus one list_discussions call per group; ~100-300 calls is typical for a wide scan. Capped at 50 groups per call."New value: +"Group ids (1-50); 1 call each."
    • changedInput schema / properties / since / description
      Previous value: -"ISO-8601 timestamp; ignore events before this time. Rejected if unparseable (so a typo can't silently widen the scan to all history)."New value: +"ISO-8601 start, rounded down to its month. Default: all history."
    • changedInput schema / properties / until / description
      Previous value: -"ISO-8601 timestamp; ignore events at or after this time. Rejected if unparseable."New value: +"ISO-8601 end (exclusive), rounded out to a whole month. Default: now."
    • changedInput schema / properties / user_id / description
      Previous value: -"Loomio user id whose activity to summarise."New value: +"Loomio user id."
  3. First observedv0.0.6

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover the read-only/idempotent profile, and the description layers on real behavioral facts beyond them: the N+1 per-group call pattern, month-granularity rounding of since/until, that anonymous polls never count, that a vote lands in the month its counted stance row was created, and that sample_events is a truncated preview rather than a full list.

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?

Highly front-loaded — scope, required inputs, returns, then caveats — and every clause carries information. The all-caps 'MONTH-GRAINED' block and dense punctuation make it slightly cramped to read, but there is no 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 no output schema, the description compensates by naming the return keys (counts, by_group, sample_events) and warning that sample_events is not exhaustive. Combined with the date-edge-case and counting rules, an agent has everything needed to call this correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds semantics the schema lacks: the fan-out implication of group_ids ('1 call each'), the acceptable provenance of user_id, and the month-widening behavior of the date bounds that the schema merely hints at.

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 resource and scope: one person's participation across a set of groups, plus the fan-out cost ('1 call per group + 1'). It does not name or contrast with the similar sibling get_participation_report, so an agent must still infer which of the two to pick.

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?

It tells the agent where user_id comes from (list_memberships or a participation row), which is useful routing for parameter sourcing, but there is no explicit when-to-use/when-not-to-use versus get_participation_report or search_content. Usage is implied by the parameter list rather than argued.

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