TeamShared

work_create

Create a work item. Created active immediately for humans and agents (no approval queue).

Creating-agent path: omitted priority → skill task-priority-assessment; omitted due_at → skill task-time-required. The distiller does not fill these. Console blanks default to priority=normal only. Result includes org + bound.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`repo`	No	Optional workspace slug tag
`tags`	No	Optional tags
`agent`	No	Override agent identity
`title`	Yes	Short task title
`due_at`	No	Optional due datetime. If omitted, fetch skill task-time-required and pass the computed due_at
`github`	No	Optional owner/repo tag
`part_of`	No	Ontology entity this beat belongs to (campaign Project name)
`priority`	No	urgent, high, normal, low. If the user/packet did not name one, fetch skill task-priority-assessment first — do not silently take the normal default	normal
`start_at`	No	Optional start datetime
`item_type`	No	task, milestone, or approval	task
`parent_id`	No	Parent task UUID (makes this a subtask)
`project_id`	No	Add the task to this project UUID
`section_id`	No	Place in this project section UUID
`assignee_id`	No	Assignee UUID
`description`	No	Alias for description_md
`work_status`	No	Initial workflow status	todo
`assignee_type`	No	Assignee type (user)
`initiative_id`	No	Optional strategic initiative UUID
`playbook_slug`	No	Named playbook to inject when agent_run_start(work_id=) spawns (e.g. teamshared-manager). Unset = no inject
`assignee_email`	No	Assign to org member by email
`description_md`	No	Optional markdown body
`assigned_to_entity`	No	Ontology Person or Agent name (graph assigned_to; not assignee_email)

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 7, 2026

changedInput schema / properties / due_at / description

Previous value: -"Optional due datetime"New value: +"Optional due datetime. If omitted, fetch skill task-time-required and pass the computed due_at"

changedInput schema / properties / priority / description

Previous value: -"urgent, high, normal, low"New value: +"urgent, high, normal, low. If the user/packet did not name one, fetch skill task-priority-assessment first — do not silently take the normal default"

Changed1 schema field changedSep 1, 2026

addedInput schema / properties / playbook_slug

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Named playbook to inject when agent_run_start(work_id=) spawns (e.g. teamshared-manager). Unset = no inject"
+}

Changed2 schema fields changedAug 30, 2026

addedInput schema / properties / assigned_to_entity

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Ontology Person or Agent name (graph assigned_to; not assignee_email)"
+}

addedInput schema / properties / part_of

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Ontology entity this beat belongs to (campaign Project name)"
+}

First observedAug 18, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It is genuinely informative: it states that created items are active immediately, there is no approval queue, the distiller does not fill omitted priority/due_at, and the result includes 'org' + 'bound'. This goes well beyond a typical 'create X' description, though it does not address permissions or reversibility.

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?

The description is compact and well-structured: a one-sentence core purpose, then a focused bullet list for the non-obvious agent-path behavior. Every sentence earns its place. The only minor weakness is the cryptic 'Result includes ``org`` + ``bound``' phrase, which is concise but under-explained.

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 22-parameter creation tool with no annotations, the description covers the most decision-critical behaviors: immediate activation, no approval queue, and the skill-invocation rules for priority and due_at. The output schema presumably documents return values, so the brief mention of result fields is acceptable. It is not exhaustive, but it gives an agent the essential context needed to call this tool correctly.

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 100%, so the baseline is 3. The description adds some value by highlighting the special behavior of omitted priority and due_at parameters and clarifying that console blanks only default priority to normal. However, it does not add meaningful semantics for the other 20 parameters, which remain fully documented only in the schema.

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 opens with a specific verb and resource: 'Create a work item.' It immediately distinguishes this tool from siblings like work_update and work_close by stating the created item becomes active immediately for both humans and agents with no approval queue. This is unambiguous and tells an agent exactly what operation this tool performs.

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

Usage Guidelines4/5

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

The description gives clear context about when this tool applies — creating work — and adds important behavioral context about the creating-agent path versus console entry: omitted priority/due_at trigger assessment skills, and console blanks default to priority=normal only. It does not explicitly name alternative tools or state when not to use it, but the creation purpose and contrast with the update/close siblings are clear enough.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.