Skip to main content
Glama

Space Monkey Mailchimp Dashboard

Get member activity timeline

sm_get_member_timeline
Read-onlyIdempotent

Replay one member's raw activity events in time order. Use to establish when someone last paid attention and what triggered it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cursorNoOpaque keyset pagination cursor returned as `nextCursor` by the previous page. Must be replayed with identical query filters.
dateToNoInclusive ISO-8601 calendar date (UTC) upper bound for the time range in YYYY-MM-DD format. Omit to leave the end of the time window unbounded or use the endpoint's default.
sortByNoThe field used to order the timeline. Defaults to ordering by the most recent timestamp first.timestamp
sortDirNoThe direction to sort the timeline results. Can be 'asc' for ascending or 'desc' for descending. Defaults to "desc" when omitted.desc
dateFromNoInclusive ISO-8601 calendar date (UTC) lower bound for the time range in YYYY-MM-DD format. Omit to leave the start of the time window unbounded.
pageSizeNoMaximum number of rows to return per page. Omit to use the default page size of 100. MCP tool calls are capped at 100 rows per page to protect the model's context window.
projectIdYesRequired. The opaque alphanumeric project identifier of 8 or more characters to scope this request to. Call GET /_api/public/v1/enterprise/projects to list the project IDs available to your API key. Omitting it returns 400 VALIDATION_ERROR.
openedFilterNoFilter timeline events to only those where the campaign was opened, not opened, or 'all' to ignore open status. Defaults to "all" when omitted.all
clickedFilterNoFilter timeline events to only those where the campaign was clicked, not clicked, or 'all' to ignore click status. Defaults to "all" when omitted.all
maxTimeToOpenNoMaximum elapsed time from the campaign send until the member's first open, in minutes. Omit to impose no upper bound.
minTimeToOpenNoMinimum elapsed time from the campaign send until the member's first open, in minutes. Omit to impose no lower bound.
subjectFilterNoFilter the timeline by a case-insensitive partial match on the campaign subject line. Omit to include all subjects.
maxTimeToClickNoMaximum elapsed time from the campaign send until the member's first click, in minutes. Omit to impose no upper bound.
minTimeToClickNoMinimum elapsed time from the campaign send until the member's first click, in minutes. Omit to impose no lower bound.
subscriberHashYesThe member's Mailchimp-style lowercase MD5 subscriber hash (canonical member key).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNoA machine-readable identifier for the error type. For the full code taxonomy, see the sm_get_schema tool or the Enterprise API OpenAPI ErrorResponse component.
dataNoResponse rows for the enclosing tool.
errorNoA human-readable error message detailing what went wrong.
hasMoreNoTrue if additional results exist beyond this page.
pageSizeNoThe maximum number of items returned in this page.
projectIdNoAn opaque alphanumeric project identifier of 8 or more characters identifying a Space Monkey Project. Treat this value as entirely opaque; do not parse, sequentialize, or auto-generate it.
nextCursorNoA keyset cursor marking the continuation point. Contract: this value is non-null if and only if `hasMore` is true. Clients MUST echo this token verbatim on the subsequent request and MUST NEVER attempt to parse or manually construct it.
subscriberHashNoThe 32-character lowercase hex MD5 hash of the member's downcased email address. This is the canonical unique identifier for members exposed across the Enterprise API, identical to Mailchimp's core behavior. The API will never expose internal synthetic BigQuery UUIDs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedOutput schema / description
      Previous value: -"Output for the sm_get_member_timeline tool. Failure payloads arrive in the same envelope as { error, message, code }."New value: +"Output for the sm_get_member_timeline tool. Failure payloads arrive in the same envelope as { error, code }."
    • addedOutput schema / properties / data / description
      Added value: +"Response rows for the enclosing tool."
    • addedOutput schema / properties / data / items / properties / activityType / description
      Added value: +"Kind of tracked action."
    • addedOutput schema / properties / data / items / properties / campaignId / description
      Added value: +"Campaign identifier, or null for non-campaign actions."
    • addedOutput schema / properties / data / items / properties / campaignTitle / description
      Added value: +"Campaign title, or null for non-campaign actions."
    • addedOutput schema / properties / data / items / properties / url / description
      Added value: +"Clicked URL, or null when absent."
  2. Changed16 schema fields changed
    • addedInput schema / properties / clickedFilter / description
      Added value: +"Filter timeline events to only those where the campaign was clicked, not clicked, or 'all' to ignore click status. Defaults to \"all\" when omitted."
    • addedInput schema / properties / cursor / description
      Added value: +"Opaque keyset pagination cursor returned as `nextCursor` by the previous page. Must be replayed with identical query filters."
    • addedInput schema / properties / dateFrom / description
      Added value: +"Inclusive ISO-8601 calendar date (UTC) lower bound for the time range in YYYY-MM-DD format. Omit to leave the start of the time window unbounded."
    • addedInput schema / properties / dateTo / description
      Added value: +"Inclusive ISO-8601 calendar date (UTC) upper bound for the time range in YYYY-MM-DD format. Omit to leave the end of the time window unbounded or use the endpoint's default."
    • addedInput schema / properties / maxTimeToClick / description
      Added value: +"Maximum elapsed time from the campaign send until the member's first click, in minutes. Omit to impose no upper bound."
    • addedInput schema / properties / maxTimeToOpen / description
      Added value: +"Maximum elapsed time from the campaign send until the member's first open, in minutes. Omit to impose no upper bound."
    • addedInput schema / properties / minTimeToClick / description
      Added value: +"Minimum elapsed time from the campaign send until the member's first click, in minutes. Omit to impose no lower bound."
    • addedInput schema / properties / minTimeToOpen / description
      Added value: +"Minimum elapsed time from the campaign send until the member's first open, in minutes. Omit to impose no lower bound."
    • addedInput schema / properties / openedFilter / description
      Added value: +"Filter timeline events to only those where the campaign was opened, not opened, or 'all' to ignore open status. Defaults to \"all\" when omitted."
    • addedInput schema / properties / pageSize / description
      Added value: +"Maximum number of rows to return per page. Omit to use the default page size of 100. MCP tool calls are capped at 100 rows per page to protect the model's context window."
    • addedInput schema / properties / projectId / description
      Added value: +"Required. The opaque alphanumeric project identifier of 8 or more characters to scope this request to. Call GET /_api/public/v1/enterprise/projects to list the project IDs available to your API key. Omitting it returns 400 VALIDATION_ERROR."
    • addedInput schema / properties / sortBy / description
      Added value: +"The field used to order the timeline. Defaults to ordering by the most recent timestamp first."
    • addedInput schema / properties / sortDir / description
      Added value: +"The direction to sort the timeline results. Can be 'asc' for ascending or 'desc' for descending. Defaults to \"desc\" when omitted."
    • addedInput schema / properties / subjectFilter / description
      Added value: +"Filter the timeline by a case-insensitive partial match on the campaign subject line. Omit to include all subjects."
    • addedInput schema / properties / subscriberHash / description
      Added value: +"The member's Mailchimp-style lowercase MD5 subscriber hash (canonical member key)."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "Output for the sm_get_member_timeline tool. Failure payloads arrive in the same envelope as { error, message, code }.",
      +  "properties": {
      +    "code": {
      +      "description": "A machine-readable identifier for the error type. For the full code taxonomy, see the sm_get_schema tool or the Enterprise API OpenAPI ErrorResponse component.",
      +      "type": "string"
      +    },
      +    "data": {
      +      "items": {
      +        "additionalProperties": true,
      +        "description": "Chronological list of all actions taken by a member.",
      +        "properties": {
      +          "activityType": {
      +            "type": "string"
      +          },
      +          "campaignId": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "campaignTitle": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "timestamp": {
      +            "description": "ISO 8601 UTC timestamp.",
      +            "type": "string"
      +          },
      +          "url": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "error": {
      +      "description": "A human-readable error message detailing what went wrong.",
      +      "type": "string"
      +    },
      +    "hasMore": {
      +      "description": "True if additional results exist beyond this page.",
      +      "type": "boolean"
      +    },
      +    "nextCursor": {
      +      "description": "A keyset cursor marking the continuation point. Contract: this value is non-null if and only if `hasMore` is true. Clients MUST echo this token verbatim on the subsequent request and MUST NEVER attempt to parse or manually construct it.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "pageSize": {
      +      "description": "The maximum number of items returned in this page.",
      +      "type": "integer"
      +    },
      +    "projectId": {
      +      "description": "An opaque alphanumeric project identifier of 8 or more characters identifying a Space Monkey Project. Treat this value as entirely opaque; do not parse, sequentialize, or auto-generate it.",
      +      "type": "string"
      +    },
      +    "subscriberHash": {
      +      "description": "The 32-character lowercase hex MD5 hash of the member's downcased email address. This is the canonical unique identifier for members exposed across the Enterprise API, identical to Mailchimp's core behavior. The API will never expose internal synthetic BigQuery UUIDs.",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description only needs to add context beyond that. It adds that events are 'raw' and returned 'in time order,' which is useful, but it does not disclose additional behavioral traits such as pagination defaults or result size. Pagination is documented in the schema, and this is acceptable given strong annotation coverage.

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?

The description is two short sentences with no filler: the first states the core action and scope, and the second gives the practical use case. Every word earns its place, and the key behavior is front-loaded.

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?

Despite the tool's 15 parameters, the full schema describes every parameter, an output schema exists, and annotations cover safety semantics. The description supplies the missing contextual layer: what the tool is for and when to use it. Nothing essential for selecting or invoking the tool 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%, and the schema already provides detailed descriptions for all 15 parameters, including defaults, formats, and constraints. The description adds little parameter-level meaning beyond implying the subscriberHash identifies the member, so the baseline of 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?

The description uses a specific verb and resource: 'Replay one member's raw activity events in time order.' This clearly identifies the tool as an event-level timeline for a single member and distinguishes it from sibling tools like sm_get_member_overview or sm_get_member_campaigns, which imply aggregated or campaign-level views.

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?

The second sentence provides an explicit intended use: 'Use to establish when someone last paid attention and what triggered it.' This gives clear context for when the tool is appropriate, though it does not explicitly state when not to use it or name alternative tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources