Skip to main content
Glama

get_tasks

Read-onlyIdempotent

Lista las tareas ABIERTAS del workspace: pendientes y en curso.

ESTADOS — son cuatro, y el backlog no es ninguno de ellos:
· pending    — pendiente, todavía no se arrancó
· wip        — en curso (`wip_since` dice desde cuándo)
· completed  — hecha      ⟶ salen por get_working_log, no por acá
· cancelled  — cancelada  ⟶ ídem
`backlog` es un booleano APARTE que convive con pending: una tarea del
backlog sigue estando pendiente, sólo que apartada del radar. Por eso no
viene en esta lista salvo que la pidas (`backlog: "incluir"` o `"solo"`).

URGENCIA — `vencidas | hoy | manana | esta_semana | proxima_semana | sin_fecha`.
Es una etiqueta DERIVADA de `due_date` contra el día de hoy en la zona
horaria del usuario, recalculada en cada llamada (la guardada en la fila
envejece sola y se devuelve aparte como `urgency_guardada`). No es una
prioridad que alguien eligió: para eso está `urgent`, que es el override
manual — "esto es urgente aunque la fecha diga que no".

VENCIMIENTO vs TRAMO — `due_date` es cuándo vence. `start_date`/`end_date`
son el tramo en la línea de tiempo y en casi todas están en NULL: eso
significa "nadie declaró cuánto dura", no "dura un día". Guardar un tramo
guarda también `due_date` igual al fin, para que las dos vistas no se
contradigan.

RESPONSABLE vs RELACIONADOS vs OWNER — son tres cosas distintas:
· `assignee_entity_id` (+ `assignee_name` resuelto) es UNA persona: la
  responsable. Es lo que contesta "¿de quién es esta tarea?".
· `related_entities.people` son MUCHAS y quiere decir "gente relacionada":
  la que aparece en la nota, la que hay que avisar, la que lo pidió.
· `owner` es `'yo' | 'otro'`: dice si se delegó, no a quién.

PRIVADAS — una tarea `private` no sale por acá ni se comparte a ningún
tablero. Pedila explícitamente con `incluir_privadas: true` si hace falta.

TODOS LOS WORKSPACES — sin `workspace_id` trae las de todos los workspaces
de la persona en una sola llamada, cada una con su `workspace`. No la llames
una vez por workspace, ni una vez por filtro si una llamada sin filtro lo cubre.

Para el detalle largo de una: get_task_detail. Para las cerradas:
get_working_log. Para lo que entra en un tablero: get_board_tasks.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMáximo resultados (default: 50)
queryNoBúsqueda parcial por título (case-insensitive, ej: 'email' encuentra 'Responder email cliente')
sourceNoDe dónde viene: 'clickup' o 'jira' (las que se traen o se subieron a esa herramienta), 'externas' (ClickUp o Jira), 'propias' (nacieron en Secondbrain). Omitir = todas
statusNoFiltrar por estado. Omitir = pending y wip
backlogNoQué hacer con el backlog (default: excluir). 'solo' contesta '¿qué dejé para después?'
urgencyNoFiltrar por urgencia derivada (la de hoy, no la guardada)
assigneeNoResponsable: nombre canónico de la persona en el Atlas, o su id numérico
con_tramoNoSólo las que tienen tramo (start_date/end_date) declarado
workspace_idNoUUID del workspace, o su nombre tal como lo dice el usuario ('Acme', 'el personal'). Omitir = TODOS los workspaces de la persona, en una sola llamada
sin_responsableNoSólo las que no tienen responsable declarado
incluir_privadasNoIncluir las tareas marcadas como privadas (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare a safe, idempotent, read-only operation, so the description correctly spends its space elsewhere: private tasks are omitted unless incluir_privadas is set, urgency is recomputed per call rather than read from storage, and omitting workspace_id fans out across all of the user's workspaces. It does not discuss result volume or paging behavior beyond the limit parameter, which keeps it out of the top band.

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?

Front-loaded correctly, with the core statement in the first line and labeled sections (ESTADOS, URGENCIA, VENCIMIENTO vs TRAMO, RESPONSABLE, PRIVADAS) that make it skimmable for an 11-parameter tool. It runs long, and the aside about saving a span also writing due_date describes a write path that is tangential to a read-only listing.

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?

With no output schema published, the description still tells the agent what comes back — each task carries its workspace, assignee_name is resolved, and the stored urgency ships separately as urgency_guardada — so the return shape is inferable. For an 11-parameter, zero-required listing tool this covers the decisions an agent must make before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so 3 is the floor, but the prose adds meaning the schema does not: urgency is derived from due_date against the user's timezone and differs from the manual 'urgent' override; backlog is an orthogonal flag rather than a fourth status; assignee_entity_id, related_entities.people and owner answer three different questions. These distinctions prevent mis-filtering that the one-line schema descriptions alone would not.

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 specific verb and resource plus a scoping qualifier: 'Lista las tareas ABIERTAS del workspace: pendientes y en curso.' It immediately narrows the domain (open only) and closes by naming the siblings that serve other slices (get_task_detail, get_working_log, get_board_tasks), so an agent can pick this tool without opening a schema.

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?

Explicit when-to-use and when-not: completed and cancelled tasks go to get_working_log, single-task depth goes to get_task_detail, board views go to get_board_tasks. It also gives a batching rule — do not call once per workspace or once per filter when an unfiltered call covers it — which is genuine routing guidance.

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