Skip to main content
Glama
bzdOS

hubd

by bzdOS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

hub_task_add

Add a task to the shared cross-project backlog, specifying project, text, and author. Optionally set category, tags, assignee, deadline, and dependencies to organize work.

Instructions

Add a task to the shared cross-project backlog.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
byYesthe function you are performing, e.g. "dev-hubd". NOT which model you are — that is read from the transcript, and many sessions share a model. NOT a queue role either: a role is a mailbox (see hub_queue_wait), this is who is at it.
catNoone of technical | communicative | decision | chore. Anything else is kept — as a tag, not a category: the four values are the axis every by-type number is counted on, so it stays closed.
tagsNofree-form labels — the open vocabulary next to the closed cat one
textYes
projectYes
verboseNoreturn the whole task object; by default the reply is {ok, id, project, by, importance, cat, textPreview} — you just wrote the text, it is not echoed back
assigneeNoagent name or owner, optional
deadlineNoYYYY-MM-DD, optional
resourcesNoresource slugs this task touches (host/vm/service/...) — a structured link task → resource, not prose
depends_onNotask ids this task waits on (bare number or a node-scoped id like "planck-3")
importanceNodefault normal

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.15
    • addedInput schema / properties / verbose
      Added value: +{
+  "description": "return the whole task object; by default the reply is {ok, id, project, by, importance, cat, textPreview} — you just wrote the text, it is not echoed back",
+  "type": "boolean"
+}
  2. Changed3 schema fields changedv0.9.0
    • changedInput schema / properties / cat / description
      Previous value: -"task category, optional"New value: +"one of technical | communicative | decision | chore. Anything else is kept — as a tag, not a category: the four values are the axis every by-type number is counted on, so it stays closed."
    • removedInput schema / properties / cat / enum
      Removed value: -[
-  "technical",
-  "communicative",
-  "decision",
-  "chore"
-]
    • addedInput schema / properties / tags
      Added value: +{
+  "description": "free-form labels — the open vocabulary next to the closed cat one",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  3. Changed4 schema fields changedv0.5.0
    • changedInput schema / properties / by / description
      Previous value: -"who adds"New value: +"the function you are performing, e.g. \"dev-hubd\". NOT which model you are — that is read from the transcript, and many sessions share a model. NOT a queue role either: a role is a mailbox (see hub_queue_wait), this is who is at it."
    • changedInput schema / properties / depends_on / description
      Previous value: -"task ids this task waits on"New value: +"task ids this task waits on (bare number or a node-scoped id like \"planck-3\")"
    • changedInput schema / properties / depends_on / items / type
      Previous value: -"integer"New value: +[
+  "integer",
+  "string"
+]
    • changedInput schema / required
      Previous value: -[
-  "project",
-  "text"
-]New value: +[
+  "project",
+  "text",
+  "by"
+]
  4. Changed1 schema field changedv0.1.8
    • addedInput schema / properties / resources
      Added value: +{
+  "description": "resource slugs this task touches (host/vm/service/...) — a structured link task → resource, not prose",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  5. First observedv0.1.6

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. 'Add' implies a mutation, but the description does not disclose permissions, side effects, duplicate handling, or any other behavioral trait beyond the basic write intent.

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 description is a single front-loaded sentence that states the core action without any wasted words. Its brevity is appropriate for the amount of information it conveys.

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?

For an 11-parameter mutation tool with no annotations and no output schema, a one-line description is too thin. It omits usage guidance, behavioral context, and any mention of return values or side effects, leaving significant gaps for an agent to fill.

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 82%, which is high enough that the schema does most of the work in explaining parameters such as 'by', 'cat', 'tags', and 'verbose'. The description itself adds no parameter-specific meaning, so the baseline score of 3 is appropriate.

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 names a specific verb and resource: 'Add a task to the shared cross-project backlog.' It clearly identifies the action and the target collection. However, it does not explicitly differentiate itself from siblings like hub_task_update or hub_task_get, relying on the verb 'Add' alone for distinction.

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?

The description gives no guidance on when to use this tool versus alternatives such as hub_task_update or hub_task_list. It does not state prerequisites, context for the shared backlog, or conditions that would select this tool over a sibling.

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