FlowCastle

create_task

Create a CRM task, on its own or linked to contacts. Creates persistent state and is NOT idempotent. Tasks live in CRM → Tasks. A task may stand alone or be linked to contacts. While leads are on for the workspace, linking parks the contact's open lead until the task is done (parkLeads, default true), and marking the task done brings the linked leads back to Waiting on us so someone tells them the result (Won and Lost leads are left alone unless named in returnContactIds). Deleting a task, or unlinking a contact, brings a lead parked on it back to Waiting on us. A task is internal work for the team: nothing is sent to anyone. With a personal key the task is owned by its user unless ownerUserId says otherwise; with a workspace key it lands unassigned.

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": {
      "title": "<title>"
    },
    "name": "create_task"
  }
}

Input Schema

Name	Required	Description
`link`	No	An issue, document or query URL the task is about.
`dueAt`	No	When it should be done, ISO 8601, e.g. "2026-11-12T09:00:00Z". A past date is allowed (it shows as overdue).
`notes`	No	Longer notes in Markdown (bold, lists, links): what to check, what was found. Plain text is fine.
`title`	Yes	Required. A short instruction a teammate understands without context, at most 200 characters.
`parkLeads`	No	Park the linked contacts' open leads until the task is done. Defaults to true.
`contactIds`	No	Contacts the task is about, as returned by list_contacts. Omit for a task of its own.
`ownerUserId`	No	Workspace member who owns it. Null for nobody. Omit for the key's user.
`applicationId`	No	Application (workspace) id. Optional: an application-scoped key (app_...) defaults to its own application, but a personal key (usr_...) has no default and omitting it fails with MCP_APPLICATION_REQUIRED. Call list_applications to get the id.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A3.9/5.0

Behavior5/5

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

The description goes well past the annotations by disclosing cross-entity side effects: linking contacts parks their open leads (parkLeads, default true), completing the task returns those leads to Waiting on us, and deleting/unlinking restores them. It also clarifies that nothing is sent to anyone, that the call is non-idempotent, and that ownership differs between personal and workspace keys — precisely the kind of context annotations cannot carry. This is consistent with readOnlyHint=false, idempotentHint=false, openWorldHint=false and destructiveHint=false.

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?

The definition is front-loaded with the action and the non-idempotency warning, then proceeds through lead lifecycle and ownership, so a reader can stop early and still call it correctly. It is dense and longer than typical, but nearly every sentence conveys a distinct behavioral fact.

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 an eight-parameter mutation with no output schema and no annotations beyond the standard hints, the description covers ownership resolution, key-type dependency on applicationId, lead side effects, and visibility (no external notification). The main omissions are what the response returns (e.g., the new task id) and how it differs from the follow-up task tool.

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 all eight parameters, making 3 the baseline. The description adds a little meaning about parkLeads defaulting to true and about ownerUserId/applicationId defaults, but it also references a "returnContactIds" parameter that does not exist in the schema, which muddies rather than clarifies parameter semantics.

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?

The opening clause gives a specific verb and resource ("Create a CRM task") plus its scope variant ("on its own or linked to contacts"), which is enough for an agent to know what it produces. It does not, however, distinguish itself from the sibling create_follow_up_task, so an agent choosing between the two task-creation tools gets no disambiguation from this text.

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?

Usage context is implied through the lead-parking and ownership discussion, which tells the agent what changes downstream when contacts are linked. There is no explicit when-to-use / when-not-to-use statement and no pointer to create_follow_up_task or update_task as alternatives, so selection against siblings 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.

All FlowCastle tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.