Skip to main content
Glama

update_task

DestructiveIdempotent

Cambia una tarea: título, descripción, fecha, urgencia, estado, tramo, responsable, backlog, entregable.

Sólo se toca lo que mandás: un campo omitido queda como estaba. Para vaciar
uno, mandá `null` explícito donde el campo lo admita.

ESTADO — pasar a `completed` escribe `completed_at`; volver a `pending`
o `wip` lo limpia. Para reabrir algo cerrado es mejor rollback_task, que
además valida que estuviera cerrado.

TRAMO — mover `end_date` mueve también `due_date`: son la misma fecha
vista de dos maneras y separarlas deja las vistas contradiciéndose.

BACKLOG no es un estado: `backlog: true` con `status: 'pending'` es una
tarea pendiente apartada del radar, y es la combinación normal.

DÓNDE VIVE — `jira_project` / `clickup_list` la mandan a ese proyecto o
lista (si todavía no estaba en ninguna herramienta, la crea allá; si ya
estaba en otra, la MUEVE), y `solo_en_secondbrain: true` evita que suba.
Se pasa UNO; get_task_destinations lista los destinos. No se puede sacar
de ClickUp/Jira una tarea que ya vive allá: eso se borra con delete_task.

Fuera de Secondbrain: si cambia el responsable, le avisa; si la tarea está en ClickUp o Jira, el cambio viaja allá.

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": {
      "task_id": "<task_id>"
    },
    "name": "update_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
ownerNoSi está delegada o no
titleNo
statusNo
urgentNoMarca de urgente a mano
backlogNoApartar del radar / traer de vuelta
privateNoSacarla o devolverla a lo compartible
task_idYesID numérico de la tarea
urgencyNo
assigneeNoResponsable: nombre canónico o id del Atlas; null lo quita
due_dateNoYYYY-MM-DD, o null para quitar
end_dateNoFin del tramo, YYYY-MM-DD o null (arrastra due_date)
start_dateNoInicio del tramo, YYYY-MM-DD o null
descriptionNo
clickup_listNoMandarla a esta lista de ClickUp: nombre o id. Ver get_task_destinations
jira_projectNoMandarla a este proyecto de Jira: clave («SB»), nombre o id. Ver get_task_destinations
workspace_idNoUUID del workspace, o su nombre tal como lo dice el usuario ('Acme', 'el personal'). Omitir si el token ya tiene workspace fijo
deliverable_idNoEntregable al que pertenece, o null
solo_en_secondbrainNoQue no suba a ClickUp ni a Jira (sólo si todavía no está en ninguna)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, destructive=true, idempotent=true, openWorld=true) by disclosing the actual side effects: status→completed writes completed_at, reverting clears it; moving end_date drags due_date; destination params create or MOVE the task in ClickUp/Jira; assignee changes trigger notifications and propagate externally. It also notes the hard limit that a task already in ClickUp/Jira cannot be pulled back here, which is exactly the kind of destructive-boundary context annotations can't express.

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 core semantics are front-loaded in the first two sentences, then the risky behaviors are grouped under labeled sections (ESTADO, TRAMO, BACKLOG, DÓNDE VIVE). Despite being multi-paragraph, every sentence carries a distinct rule or caveat and none repeats the schema.

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 18-parameter mutation tool with no output schema, the description covers the high-risk semantics thoroughly: partial updates, clearing, status transitions, date coupling, and cross-tool propagation. It stops short of describing the response payload or error/validation behavior, which is the only remaining gap an agent would care about.

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?

With 78% schema coverage the baseline is 3, and the description adds real meaning the schema does not: the end_date/due_date coupling, backlog not being a status (backlog:true + status:'pending' is the normal combination), and the rule that only ONE of jira_project/clickup_list/solo_en_secondbrain may be passed. It leaves owner, private, and urgency without added explanation, so it is not exhaustive.

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?

Opens with a concrete verb+resource ("Cambia una tarea") and enumerates the mutable fields (título, descripción, fecha, urgencia, estado, tramo, responsable, backlog, entregable), which maps directly onto the schema. It also names siblings and their distinct roles (rollback_task for reopening, delete_task for removal), so an agent can tell it apart from neighboring tools.

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?

Explicitly states the partial-update contract (omitted fields stay untouched), how to clear a field (explicit null), and routes to alternatives with conditions: rollback_task when reopening a closed task, get_task_destinations to list destinations, delete_task to pull a task out of ClickUp/Jira. When-to-use and when-not-to-use are both covered.

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