Skip to main content
Glama
eabz

Tirith

Official
by eabz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

task_pull

Get work by claiming the highest-priority todo whose dependencies are done, making it in_progress for your agent. It prefers unclaimed paths and can wait server-side, avoiding polling.

Instructions

Take the next task: the highest-priority todo whose dependencies are done becomes in_progress and yours, preferring tasks whose paths nobody else holds. Use to get work; to look without taking use task_list, and to change a named task use task_update. none means nothing is unblocked; a task that comes with waiting_on overlaps paths others hold, so coordinate before editing them. wait_secs waits server-side for work instead of you polling.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agentYesYour stable agent name.
wait_secsNoWait up to this many seconds (max 120) while todo tasks are claimed or wait on dependencies.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskNoThe task you now own: 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).
statusYesok: the task is yours, in_progress. none: no todo task is unblocked. cancelled: a wait whose caller left. invalid: bad input.
messageNoHuman-readable detail, on most outcomes other than ok.
waiting_onNoPresent when the task's paths overlap what others hold: path, owner. Coordinate before editing those.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.1.2
    • addedInput schema / properties / agent / description
      Added value: +"Your stable agent name."
    • addedInput schema / properties / wait_secs / description
      Added value: +"Wait up to this many seconds (max 120) while todo tasks are claimed or wait on dependencies."
    • 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"
+    },
+    "status": {
+      "description": "ok: the task is yours, in_progress. none: no todo task is unblocked. cancelled: a wait whose caller left. invalid: bad input.",
+      "enum": [
+        "ok",
+        "conflict",
+        "not_found",
+        "none",
+        "invalid",
+        "cancelled"
+      ],
+      "type": "string"
+    },
+    "task": {
+      "description": "The task you now own: 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"
+    },
+    "waiting_on": {
+      "description": "Present when the task's paths overlap what others hold: path, owner. Coordinate before editing those.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}
  2. First observedv1.1.1

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the sparse annotation (destructiveHint=false), the description discloses that the selected task 'becomes in_progress and yours', describes the path-preference selection strategy, clarifies that wait_secs 'waits server-side for work instead of you polling,' and explains the meaning of 'none' and 'waiting_on' for coordination. There is no contradiction with 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?

Every sentence earns its place: the first delivers the core action and selection rule, the second routes to alternatives, and the third clarifies return semantics and the wait parameter. The most important information is front-loaded, and there is no filler or repetition of schema content.

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 tool's moderate complexity, an output schema exists, and the annotation is minimal, the description covers selection algorithm, side effect (ownership), usage alternatives, and edge-case interpretation ('none' and 'waiting_on'). It provides everything an agent needs to invoke the tool correctly and handle the result, making it complete for its context.

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 baseline is 3 with both parameters already documented. The description adds extra behavioral nuance for wait_secs ('waits server-side for work instead of you polling') that is not in the schema, lifting it above baseline. The agent parameter is not further elaborated, but the schema's 'Your stable agent name' is sufficient.

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 'Take the next task' – a specific verb and resource – then precisely defines the selection criteria (highest-priority todo with dependencies done, becoming in_progress and yours). It also explicitly differentiates from task_list and task_update, so an agent can distinguish the tool from key siblings without opening schemas.

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?

The description states exactly when to use this tool ('Use to get work') and when not to, naming alternatives: 'to look without taking use task_list, and to change a named task use task_update.' It also provides post-return guidance about interpreting 'none' and coordinating on 'waiting_on' tasks, covering when-to-use and exclusion criteria explicitly.

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