TeamShared

work_list

List org work items (shared task queue for humans and agents).

Input Schema

Name	Required	Description	Default
`tag`	No	Only items carrying this label
`mine`	No	Only items assigned to the caller (human or agent)
`sort`	No	Sort key	updated_at
`limit`	No
`offset`	No	Pagination offset
`compact`	No	Omit description_md and actor objects. Keep id, title, work_status, due_at, priority, assignee_label and project names. Console chat turns this on when the argument is omitted
`has_due`	No	True: only dated items; False: only undated
`assignee`	No	Filter by user email, agent name, actor id, or 'unassigned'. Names that match nobody return no items
`due_from`	No	Inclusive start of due_at window (UTC)
`sort_dir`	No	asc or desc	desc
`due_until`	No	Exclusive end of due_at window (UTC)
`item_type`	No	Filter: task, milestone, or approval
`project_id`	No	Filter to work linked to this project UUID
`work_status`	No	Filter by workflow status
`closed_since`	No	Also include items closed at or after this instant (UTC)
`initiative_id`	No	Filter to tasks linked to a strategic initiative UUID
`work_statuses`	No	Match any of these statuses (e.g. todo, in_progress, blocked)
`exclude_closed`	No	Omit done/cancelled items (default true)
`include_cancelled`	No	False drops cancelled items (default true)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026

addedInput schema / properties / compact

Added value: +{
+  "default": false,
+  "description": "Omit description_md and actor objects. Keep id, title, work_status, due_at, priority, assignee_label and project names. Console chat turns this on when the argument is omitted",
+  "type": "boolean"
+}

Changed2 schema fields changedOct 11, 2026

changedInput schema / properties / work_status / anyOf

Previous value: -[
-  {
-    "enum": [
-      "backlog",
-      "todo",
-      "in_progress",
-      "blocked",
-      "done",
-      "cancelled"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "backlog",
+      "todo",
+      "in_progress",
+      "in_review",
+      "blocked",
+      "done",
+      "cancelled"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / work_statuses / anyOf

Previous value: -[
-  {
-    "items": {
-      "enum": [
-        "backlog",
-        "todo",
-        "in_progress",
-        "blocked",
-        "done",
-        "cancelled"
-      ],
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "enum": [
+        "backlog",
+        "todo",
+        "in_progress",
+        "in_review",
+        "blocked",
+        "done",
+        "cancelled"
+      ],
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

Changed6 schema fields changedSep 27, 2026

changedInput schema / properties / assignee / description

Previous value: -"Filter by agent name or user email"New value: +"Filter by user email, agent name, actor id, or 'unassigned'. Names that match nobody return no items"

addedInput schema / properties / closed_since

Added value: +{
+  "anyOf": [
+    {
+      "format": "date-time",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Also include items closed at or after this instant (UTC)"
+}

addedInput schema / properties / include_cancelled

Added value: +{
+  "default": true,
+  "description": "False drops cancelled items (default true)",
+  "type": "boolean"
+}

changedInput schema / properties / sort / enum

Previous value: -[
-  "updated_at",
-  "priority",
-  "work_status",
-  "created_at"
-]New value: +[
+  "updated_at",
+  "priority",
+  "work_status",
+  "created_at",
+  "due_at"
+]

addedInput schema / properties / tag

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Only items carrying this label"
+}

addedInput schema / properties / work_statuses

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "enum": [
+          "backlog",
+          "todo",
+          "in_progress",
+          "blocked",
+          "done",
+          "cancelled"
+        ],
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Match any of these statuses (e.g. todo, in_progress, blocked)"
+}

Changed5 schema fields changedSep 7, 2026

addedInput schema / properties / due_from

Added value: +{
+  "anyOf": [
+    {
+      "format": "date-time",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Inclusive start of due_at window (UTC)"
+}

addedInput schema / properties / due_until

Added value: +{
+  "anyOf": [
+    {
+      "format": "date-time",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Exclusive end of due_at window (UTC)"
+}

addedInput schema / properties / has_due

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "True: only dated items; False: only undated"
+}

addedInput schema / properties / item_type

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "task",
+        "milestone",
+        "approval"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Filter: task, milestone, or approval"
+}

addedInput schema / properties / project_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Filter to work linked to this project UUID"
+}

First observedAug 18, 2026

TDQS

C2.8/5.0

Behavior2/5

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

With no annotations, the description carries the full burden, yet it discloses nothing about the behavior that matters most here: closed items are excluded by default (exclude_closed=true), cancelled items are still included, pagination defaults to 50/200 cap, and compact mode trims fields. The parenthetical 'shared task queue for humans and agents' adds conceptual context but no operational detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero waste, which is good, but for a 19-parameter listing tool with non-obvious default exclusions the brevity reads as under-specification rather than disciplined concision.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema covers return values and the input schema is richly described, but the description omits the behavioural default that most affects results: done/cancelled filtering is governed by exclude_closed (true) and include_cancelled (true), which is easy to misread. For a tool with 19 params and no annotations, the description should do more.

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 95%, so nearly every one of the 19 parameters is already self-documenting (assignee matching rules, due window inclusivity/exclusivity, compact field list). The description adds nothing about parameters, so it sits at the baseline 3 where the schema does the work.

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 description states a specific verb and resource ('List org work items') and adds a clarifying gloss (shared task queue for humans and agents), which is more informative than the bare tool name. It doesn't explicitly differentiate itself from near-neighbours like project_list, process_run_list, or review_list, so it falls short of a 5.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives (e.g. work_get for a single item, project_list for project views), and no mention of prerequisites or typical call patterns. The agent must infer usage entirely from the name and schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TeamShared tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.