Skip to main content
Glama
Selerity

accelo-mcp

by Selerity
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

accelo_create_activity

Create a new activity (note, email, call, or meeting).

Instructions

Create a new activity (note, email, call, or meeting).

Owner vs recipients: owner_type/owner_id set the activity's SENDER (the from/author interaction). The to/cc/bcc arguments set the RECIPIENT interactions and are independent of the owner. Naming a recipient under to now addresses the activity TO them — this fixes the previous behaviour where a non-owner recipient was recorded as bcc.

Each of to/cc/bcc is an object keyed by one or more of: - staff: list of staff ids (ints) - affiliation: list of affiliation ids (ints) - emails: list of raw email address strings For example: to={"staff": [10]}, cc={"affiliation": [13, 14]}, bcc={"emails": ["person@example.com"]}.

Supplying any of to/cc/bcc sends the request to Accelo as a single JSON body (the normal activity fields plus the recipient objects). Raw emails passed under emails create no interact object on the Accelo side (this is expected). When none of to/cc/bcc is supplied the activity is sent via the existing form-encoded path, unchanged.

Args: subject: Activity subject (required) against_type: Object type to create against (required). E.g. company, job, issue, staff, task against_id: ID of the object to create against (required) body: Activity body/content medium: Type — 'note', 'meeting', 'email', or 'call' (default: note) priority_id: Priority ID class_id: Activity class ID owner_type: Owner type ('staff' or 'affiliation'). Sets the SENDER (from/author), not a recipient. owner_id: Owner ID (staff_id or affiliation_id). Sets the SENDER. billable: Billable time in seconds nonbillable: Non-billable time in seconds task: Task ID to log the activity against. To log time against a task, set against_type/against_id to the task's PARENT (job/milestone/issue) and pass the task ID here (sent to Accelo as task_id). visibility: Activity visibility — 'private' (default), 'confidential', or 'all'. MUST be 'all' to log billable/non-billable time; the Accelo default of 'private' silently prevents time logging. date_started: Start date as a unix timestamp (seconds since UTC). For meetings this is the scheduled start; for other activities it sets the logged date (date_logged derives from date_started, falling back to date_created when unset). to: TO recipients — object keyed by staff/affiliation/emails, e.g. {"staff": [10]}. Addresses the activity TO these recipients. cc: CC recipients — object keyed by staff/affiliation/emails, e.g. {"affiliation": [13, 14]}. bcc: BCC recipients — object keyed by staff/affiliation/emails, e.g. {"emails": ["person@example.com"]}. fields: Additional fields to return

Input Schema

NameRequiredDescriptionDefault
ccNo
toNo
bccNo
bodyNo
taskNo
fieldsNo
mediumNo
subjectYes
billableNo
class_idNo
owner_idNo
against_idYes
owner_typeNo
visibilityNo
nonbillableNo
priority_idNo
against_typeYes
date_startedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.5.0
    • addedInput schema / properties / bcc
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "items": {},
+        "type": "array"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Bcc"
+}
    • addedInput schema / properties / cc
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "items": {},
+        "type": "array"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Cc"
+}
    • addedInput schema / properties / to
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "items": {},
+        "type": "array"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "To"
+}
  2. Changed3 schema fields changedv0.2.1
    • addedInput schema / properties / date_started
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Date Started"
+}
    • addedInput schema / properties / task
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Task"
+}
    • addedInput schema / properties / visibility
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Visibility"
+}
  3. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so substantively: it explains the owner-as-sender vs recipient distinction, that supplying to/cc/bcc switches the payload to a JSON body while omitting them uses form-encoding, that raw `emails` create no interact object, and that 'private' visibility silently blocks time logging. It does not cover auth/permission requirements, idempotency, or whether creating an email activity actually dispatches mail.

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?

Given 18 parameters and zero schema documentation, the length is justified, and the core purpose plus the owner-vs-recipient rule are front-loaded. Some content does not earn its place — the changelog aside about the previous bcc behaviour is release-note noise rather than decision-relevant guidance.

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 complex 18-parameter mutation tool with no annotations and no output schema, the description is nearly complete: it covers all parameter semantics, the payload-format switch, and the visibility gotcha. The notable gaps are a lack of stated return values (no output schema exists to defer to) and no mention of permission requirements or side effects from email/meeting activities.

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 description coverage is 0%, so the description must compensate and largely does — it defines the to/cc/bcc keyed object structure with concrete examples, clarifies owner_type/owner_id as sender rather than recipient, specifies date_started as a unix timestamp with different meaning for meetings, and constrains visibility values. A few entries remain tautological (`priority_id: Priority ID`, `class_id: Activity class ID`, `fields: Additional fields to return`), which keeps it from a 5.

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 and resource — "Create a new activity (note, email, call, or meeting)" — and names the four activity mediums up front. It does not explicitly contrast itself with the sibling create/update/delete activity tools, but the verb makes its position unambiguous.

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?

There is strong conditional guidance for parameters (e.g., "To log time against a task, set against_type/against_id to the task's PARENT...", and "visibility MUST be 'all' to log billable/non-billable time"), but no explicit statement of when to choose this tool over siblings like accelo_update_activity or which activity types map to which use case. Usage is implied rather than framed.

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