Tirith

Official

Overview Schema Source Related Servers Discussions Admin

task_update

Idempotent

Change a task's status to done, todo, blocked with reason, or in_progress. Resolve conflicts with other agents by force, then get the full task.

Instructions

Change one task's status: done to finish it, todo to hand it back, blocked to park it with note as the reason, in_progress to take it by id. Changing a task another agent has in_progress is a conflict naming the owner, unless force, which is recorded in the task's notes. To get the next task without naming one use task_pull. Returns the task in full.

Input Schema

TableJSON Schema

Name	Required	Description
`note`	No	A note to append. For `blocked`, this is the reason.
`agent`	Yes	Your stable agent name.
`force`	No	Take or close a task another agent has in progress.
`status`	Yes	One of `todo`, `in_progress`, `blocked`, `done`.
`task_id`	Yes	The task's id, or a unique prefix of it.

Output Schema

TableJSON Schema

Name	Required	Description
`task`	No	The task after the change: id, title, description, priority, depends_on, paths, created_by, created_at, updated_at, notes, and state: its status with owner (in_progress), owner and reason (blocked), or by (done).
`owner`	No	On conflict: the agent that has the task in_progress.
`since`	No	On conflict: RFC 3339 time that agent took it.
`status`	Yes	ok. conflict: another agent has it in_progress and force was not set. not_found: no such task. invalid: bad status or an ambiguous id prefix.
`message`	No	Human-readable detail, on most outcomes other than ok.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv1.1.2Sep 18, 2026

addedInput schema / properties / agent / description
```
Added value: +"Your stable agent name."
```

addedInput schema / properties / force / description

Added value: +"Take or close a task another agent has in progress."

addedInput schema / properties / note / description

Added value: +"A note to append. For `blocked`, this is the reason."

addedInput schema / properties / status / description

Added value: +"One of `todo`, `in_progress`, `blocked`, `done`."

addedInput schema / properties / status / enum

Added value: +[
+  "todo",
+  "in_progress",
+  "blocked",
+  "done"
+]

addedInput schema / properties / task_id / description

Added value: +"The task's id, or a unique prefix of it."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Any result may also carry lost, inbox, inbox_more and persist_error; see guide.",
+  "properties": {
+    "message": {
+      "description": "Human-readable detail, on most outcomes other than ok.",
+      "type": "string"
+    },
+    "owner": {
+      "description": "On conflict: the agent that has the task in_progress."
+    },
+    "since": {
+      "description": "On conflict: RFC 3339 time that agent took it."
+    },
+    "status": {
+      "description": "ok. conflict: another agent has it in_progress and force was not set. not_found: no such task. invalid: bad status or an ambiguous id prefix.",
+      "enum": [
+        "ok",
+        "conflict",
+        "not_found",
+        "none",
+        "invalid",
+        "cancelled"
+      ],
+      "type": "string"
+    },
+    "task": {
+      "description": "The task after the change: id, title, description, priority, depends_on, paths, created_by, created_at, updated_at, notes, and state: its status with owner (in_progress), owner and reason (blocked), or by (done).",
+      "type": "object"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

First observedv1.1.1Sep 18, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond the idempotentHint and destructiveHint annotations, the description discloses conflict behavior when another agent has the task in_progress, the meaning and effect of force, and that the action is recorded in the task's notes. It also states the return value is the full task, adding useful behavioral context not present in annotations.

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?

Three dense sentences deliver the essential information in order: status semantics, conflict/force rules, alternative routing, and return value. There is no filler or repetition of schema details.

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?

Given the output schema exists and annotations cover safety, the description sufficiently covers all status transitions, conflict handling, force behavior, note usage, return shape, and the main sibling alternative. Nothing important is missing for an agent to invoke the tool correctly.

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 coverage is 100%, so the baseline is 3, but the description adds real semantic value by explaining what each status means in context: done finishes, todo hands back, blocked parks with a note as reason, and in_progress takes by id. It also clarifies the force/note interaction beyond the raw parameter descriptions.

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: 'Change one task's status,' then maps each allowed status to its intended effect. It also distinguishes itself from task_pull by pointing users to that sibling for getting the next task without naming one.

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?

It clearly states when to use the tool and gives an explicit alternative: 'To get the next task without naming one use task_pull.' It also explains the conflict scenario and force flag. It doesn't enumerate all sibling exclusions like task_create or task_list, but the primary routing guidance is solid.

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