Skip to main content
Glama

Job: Get Task Status

get_job_status
Read-onlyIdempotent

[SystemInternal] [What it does] Reads the latest status of one asynchronous task created by a DSers business write tool, using the exact task_type and task_id returned by that creating tool. [When to use] Use when the user asks whether an earlier async action has finished or what stage it is at. [When not to use] Never use this to create, cancel, or rerun a task; it is read-only status only. Legacy job_id queries are unsupported, and only one task can be queried per call. [How to use] Copy task_type and task_id exactly from the creating Tool. delay_seconds is optional (default 3, max 20). terminal=true means polling can stop, but still inspect status and error. When status is unknown, never automatically retry the original write; verify the business entity instead. Product push, price sync, AI mapping, and supply-order sync actively refresh upstream state; stock sync only confirms receipt. The current or final task-specific business outcome is carried in result. For order_process, copy the task ID returned by place_orders_to_suppliers. [Side effects] None; read-only and never creates, cancels, or retries a business write. [Confirmation] Not required.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_type": "<task_type>",
      "task_id": "<task_id>"
    },
    "name": "get_job_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYesRequired opaque task ID copied exactly from the same asynchronous tool result.
task_typeYesRequired business task type copied exactly from the asynchronous tool result.
delay_secondsNoSeconds to wait before reading task storage and querying any live upstream status. Defaults to 3; maximum 20.

Output Schema

NameRequiredDescriptionDefault
errorNoTerminal or current task error
totalYesTotal work units
resultNoCurrent or terminal business result. Task-specific fields are returned here.
statusYesCurrent task status
messageNoCurrent status message
task_idNoTask identifier returned by the upstream business service
progressYesCompleted work units
terminalYesWhether no further status polling is required
warningsNoNon-blocking status warnings
task_typeNoBusiness asynchronous task type
updated_atYesLast persisted task update
poll_after_secondsNoRecommended delay before the next status read
toolcall_response_atYesUTC timestamp when the Tool response was returned, formatted as RFC3339.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: no confirmation required, no side effects, polling ('terminal=true means polling can stop'), and the divergence in upstream refresh behavior between task types. The only missing piece is what a failed or timed-out read looks like on the response side, though the output schema may cover that.

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 broadcast label structure is front-loaded and easy to scan, and each section carries distinct information. The text is dense, not padded, though a few clauses (for example repeating that it is read-only across [When not to use] and [Side effects]) could be consolidated.

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?

Considering that the output schema exists, this description covers everything an agent needs in order to call the tool correctly. It states what the tool does, when to use it, how to fill in the parameters, and how to read the result (status, error, result, terminal). It also clarifies the handling of unknown status states.

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 all three parameters are already documented, and the tool contract states the same 'copy exactly' rule that the schema does. The description's unique contribution is the type-specific hint that for `order_process` the task ID comes from `place_orders_to_suppliers` and that task_type must match the creating tool's enum value; this is useful but not decisive.

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: 'Reads the latest status of one asynchronous task created by a DSers business write tool.' It also scopes the tool ('one task', 'read-only status only'), which clearly separates it from the write siblings like place_orders_to_suppliers or apply_ai_mapping.

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?

Explicit [When to use] and [When not to use] sections name the condition ('whether an earlier async action has finished'), the exclusions (no create/cancel/rerun, no legacy job_id, one task per call), and the fallback behavior ('verify the business entity instead'). This leaves no inference required about when to select this tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.