Skip to main content
Glama
CronusL-1141

AI Team OS

by CronusL-1141
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

task_list_project

Retrieve project or team task wall with a digest summary and compact task rows. Filter by status, priority, or horizon to monitor pending work.

Instructions

Get the task wall — project-scoped by default, team-scoped on request.

Pass team_id to narrow the wall to one team; leave it empty to get every team under the project plus the project-level tasks that belong to no team.

Project scope leads with digest: the whole wall in one text block (open counts by status and horizon, 7-day trend, stale and dormant counts, the 5 most recent actions, the top 5 pending, the first mid and long pending task). It is the same block the session briefing shows; read it first, the rows below are one page.

Default response is a COMPACT projection (marked by view="compact" + hint — it is a trimmed view, NOT missing fields): each task row keeps id/title/priority/status/score/assigned_to/tags + 80-char desc excerpt (plus result/depends_on/subtask_count when present). Full details of a single task: task_status(task_id) / task_memo_read(task_id).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax number of pending tasks to return (default 50; project scope only). Running, blocked and failed tasks always come back in full; not_shown counts the pending tasks left off the page.
fieldsNo"compact" (default, trimmed projection) / "all" (full rows)compact
offsetNoPagination offset for pending tasks (default 0; project scope only)
statusNoFilter by status: pending/running/blocked/failed/completed (default: every status except completed; project scope only). status="completed" returns rows only together with include_completed=True; on its own it yields an empty wall.
horizonNoFilter by time horizon: "short" / "mid" / "long" (optional)
team_idNoTeam ID or name — narrows the wall to one team (optional)
priorityNoFilter by priority: "critical" / "high" / "medium" / "low" (optional; comma-separated accepted for multiple)
project_idNoProject ID (optional, auto-uses active project if empty; ignored when team_id is given)
include_completedNoInclude completed tasks (default False; project scope only)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.15.0
    • changedInput schema / properties / limit / description
      Previous value: -"Max number of active tasks to return (default 50; project scope only)"New value: +"Max number of pending tasks to return (default 50; project scope\nonly). Running, blocked and failed tasks always come back in full;\nnot_shown counts the pending tasks left off the page."
    • changedInput schema / properties / offset / description
      Previous value: -"Pagination offset for active tasks (default 0; project scope only)"New value: +"Pagination offset for pending tasks (default 0; project scope only)"
    • changedInput schema / properties / status / description
      Previous value: -"Filter by status: pending/running/blocked/completed\n(default all active; project scope only)"New value: +"Filter by status: pending/running/blocked/failed/completed\n(default: every status except completed; project scope only).\nstatus=\"completed\" returns rows only together with\ninclude_completed=True; on its own it yields an empty wall."
  2. Changed8 schema fields changedv1.11.2
    • addedInput schema / properties / fields
      Added value: +{
+  "default": "compact",
+  "description": "\"compact\" (default, trimmed projection) / \"all\" (full rows)",
+  "type": "string"
+}
    • changedInput schema / properties / include_completed / description
      Previous value: -"Include completed tasks in response (default False)"New value: +"Include completed tasks (default False; project scope only)"
    • changedInput schema / properties / limit / description
      Previous value: -"Max number of active tasks to return (default 50)"New value: +"Max number of active tasks to return (default 50; project scope only)"
    • changedInput schema / properties / offset / description
      Previous value: -"Pagination offset for active tasks (default 0)"New value: +"Pagination offset for active tasks (default 0; project scope only)"
    • changedInput schema / properties / priority / description
      Previous value: -"Filter by priority: \"critical\" / \"high\" / \"medium\" / \"low\" (optional)"New value: +"Filter by priority: \"critical\" / \"high\" / \"medium\" / \"low\"\n(optional; comma-separated accepted for multiple)"
    • changedInput schema / properties / project_id / description
      Previous value: -"Project ID (optional, auto-uses active project if empty)"New value: +"Project ID (optional, auto-uses active project if empty;\nignored when team_id is given)"
    • changedInput schema / properties / status / description
      Previous value: -"Filter by status: pending/running/blocked/completed (default all active)"New value: +"Filter by status: pending/running/blocked/completed\n(default all active; project scope only)"
    • addedInput schema / properties / team_id
      Added value: +{
+  "default": "",
+  "description": "Team ID or name — narrows the wall to one team (optional)",
+  "type": "string"
+}
  3. First observedv1.9.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the disclosure burden, and it does real work here: it explains that team_id is ignored when project_id conflicts, that limit/offset/status/include_completed only apply in project scope, that running/blocked/failed rows always return in full, and that view="compact" is a trimmed projection rather than a missing-field error. It does not state the read-only nature or permission requirements, which is the main remaining gap.

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 with the scope decision, then the digest, then the projection caveat — a sensible priority order for an agent. It is somewhat long and repeats elements that the schema already spells out (e.g., the completed/status interaction), but every paragraph carries at least one non-redundant 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 a 9-parameter list tool with an output schema, the description covers what an agent must know before calling: default scope, what team_id does, that the digest should be read first, and how pagination applies. Return-shape detail is partly redundant with the output schema, and the read-only/safety profile is left implicit, so it falls just short of fully complete.

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 100%, so the schema already documents every parameter and the baseline is 3. The description adds meaning beyond that by framing the compact projection as a deliberate trim (hinting rows always carry id/title/priority/status/score/assigned_to/tags plus an 80-char excerpt) and by describing the digest's contents, which the schema does 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?

The opening sentence names a specific verb and resource ('Get the task wall') and immediately states the default scope vs the on-request scope, which is exactly the distinction an agent needs. It also distinguishes itself from the sibling read tools task_status and task_memo_read by naming them for the single-task case.

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 routing rules: pass team_id to narrow to one team, leave it empty for project-wide plus unteamed tasks; read the digest block first because the rows are only one page; use task_status/task_memo_read for a single task's full details. When-and-when-not is covered, along with the alternative tools.

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