Skip to main content
Glama

poll_tasks

Read-onlyIdempotent

Waits for new task assignments and returns open tasks plus whether work changed, blocking until a task arrives or the timeout expires.

Instructions

Long-poll for new task assignments: use it only in a loop that waits for work. Blocks until a task is assigned to this agent or the timeout expires. Returns your open tasks (in_progress, review, todo; at most limit, with total_count/has_more) and whether any change occurred; done, cancelled and backlog need status_category or full=true. Tasks use the lean get_my_tasks view (first-line descriptions, no envelope fields); full=true returns the complete items without the open-category default. Kept for backward compatibility; get_my_tasks is the non-blocking equivalent.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "poll_tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
fullNoReturn complete task items of every status category instead of the lean open-card view (default false).
limitNoMax results (default 50).
timeoutNoMaximum seconds to wait for new assignments (default 30, max 120).
project_idNoFilter by project.
status_categoryNoFilter by status category, one or a comma list: backlog, todo, in_progress, review, done, cancelled. Default: in_progress,review,todo.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.8
    • changedInput schema / properties / full / description
      Previous value: -"Return complete task items instead of the lean view (default false)."New value: +"Return complete task items of every status category instead of the lean open-card view (default false)."
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Max results (default 50).",
      +  "type": "number"
      +}
    • addedInput schema / properties / project_id
      Added value: +{
      +  "description": "Filter by project.",
      +  "type": "string"
      +}
    • addedInput schema / properties / status_category
      Added value: +{
      +  "description": "Filter by status category, one or a comma list: backlog, todo, in_progress, review, done, cancelled. Default: in_progress,review,todo.",
      +  "type": "string"
      +}
  2. First observedv0.1.1

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the read-only and idempotent annotations, the description discloses blocking until assignment or timeout, return shape including total_count/has_more, lean-view defaults, and how full=true changes category behavior. This adds substantial behavioral context that annotations alone do not provide.

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 dense but front-loaded with the loop-only usage and blocking behavior. Most sentences carry operational meaning, though the return-shape sentence is somewhat crowded and could be split for readability.

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?

With no output schema, the description still explains what is returned, including open-category defaults, the lean view, and full=true behavior. It adequately covers a polling tool whose main behavioral risks are blocking and default filtering.

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 already 100%, so the baseline is 3, but the description adds useful cross-parameter meaning: full=true returns complete items without the open-category default, and done/cancelled/backlog categories require status_category or full=true. It also notes the limit cap and timeout semantics in prose.

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 states a specific verb and resource: long-polling for task assignments. It distinguishes the tool from get_my_tasks by explicitly naming it as the non-blocking equivalent and by describing blocking loop behavior.

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?

It says to use this tool only in a loop that waits for work, and identifies get_my_tasks as the non-blocking alternative. The backward-compatibility note further clarifies when another tool may be preferred.

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