Skip to main content
Glama
soil-dev

capsulemcp

by soil-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

update_task

Change existing task details, due dates, status, owner, or parent link. Only supplied fields update, and a parent can be re-linked or cleared with null.

Instructions

Update fields on an existing task: description, dueOn, dueTime, detail, status (OPEN or COMPLETED), ownerId, and the parent-reference fields partyId, opportunityId, projectId. Pass a parent id to re-link the task, or null on a parent field to orphan/unlink it; at most one parent id may be set in a single call, though null+id swaps are allowed. Only the fields you provide are changed. To mark a task done, prefer the dedicated complete_task tool — it's idempotent (a no-op success on an already-completed task) and semantically clearer than update_task status=COMPLETED. Capsule rejects directly setting status=PENDING (which exists only internally for track-driven tasks); use OPEN or COMPLETED. Completed tasks remain fully editable — Capsule does not enforce closed-record immutability.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
dueOnNoYYYY-MM-DD
detailNo
statusNoSet to OPEN or COMPLETED. (PENDING exists internally for track-driven tasks but cannot be set directly via this tool — Capsule rejects it.) Setting status: OPEN on an already-open task is a true no-op (does not advance updatedAt).
dueTimeNoHH:MM in user's timezone
ownerIdNoReassign owner to user ID. Once set, this connector cannot clear an owner back to null — use Capsule's web UI for that.
partyIdNoRe-link the task to a party by id, or `null` to orphan it. Mutually exclusive with `opportunityId` / `projectId` — Capsule enforces 'task can be related to at most one entity' server-side (422 if two parent-refs are set at once, verified in v1.6.3 wire-trace). To swap parent type atomically, pass the old one as `null` and the new one as an id in the same call. NOTE: orphaning is unique to tasks — `update_opportunity.partyId` and `update_project.partyId` are NOT nullable (Capsule rejects with 422 'party is required'). Tasks are the only entity in Capsule's data model that can exist without any parent.
projectIdNoRe-link the task to a project by id, or `null` to orphan it. Mutually exclusive with `partyId` / `opportunityId` — see `partyId` for the XOR semantic.
descriptionNo
opportunityIdNoRe-link the task to an opportunity by id, or `null` to orphan it. Mutually exclusive with `partyId` / `projectId` — see `partyId` for the XOR semantic.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.0
    • addedInput schema / required
      Added value: +[
+  "id"
+]
  2. Changed1 schema field changedv2.1.2
    • changedInput schema / properties / projectId / description
      Previous value: -"Re-link the task to a project (kase) by id, or `null` to orphan it. Mutually exclusive with `partyId` / `opportunityId` — see `partyId` for the XOR semantic."New value: +"Re-link the task to a project by id, or `null` to orphan it. Mutually exclusive with `partyId` / `opportunityId` — see `partyId` for the XOR semantic."
  3. Addedv1.7.0
  4. Removedv1.6.2
  5. First observedv1.0.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only indicate a non-readonly, non-destructive mutation; the description goes far beyond by disclosing partial updates, no-op success semantics, that completed tasks remain editable, and that parent fields support null-orphaning with at-most-one-parent enforcement. This is valuable behavioral context that annotations do not provide, and there is no contradiction.

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?

Although the description is dense, every sentence earns its place: the opening sentence enumerates fields, the middle clarifies parent semantics and partial updates, and the closing sentences give routing and status constraints. It is front-loaded with the primary purpose before diving into edge cases.

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?

For a 10-parameter mutation tool with no output schema and minimal annotations, the description covers the critical invocation context: updatable fields, parent re-linking/orphaning, status limitations, and post-update mutability. No key behavior an agent would need to call it correctly is missing.

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 70%, and the description reinforces and extends parameter meaning by explicitly stating the parent-field XOR rule, null+id swap behavior, and 'only the fields you provide are changed.' It relies on the schema for field-level details like patterns and owner clearing, but the body description still adds group-level semantics not obvious from individual parameter definitions.

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 states a specific verb and resource ('Update fields on an existing task') and enumerates the exact fields, so an agent knows precisely what the tool does. It also distinguishes itself from the sibling complete_task by naming it and explaining the semantic difference for marking tasks done.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to prefer complete_task for marking a task done, providing a clear routing rule to an alternative. It also specifies when not to use certain values (status=PENDING is rejected) and describes the partial-update behavior so an agent knows only provided fields are changed.

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