Skip to main content
Glama
Sign In

DeepScout

by ai.deepscout
OverviewDiscussionsAdmin

Get the state of a job

scout_get_job
Read-only

Get the state of a job: status, estimate, approval, settlement, and error. Poll every 5 to 10 minutes until the status is COMPLETED, FAILED, or CANCELLED. The time depends on the number of products, because DeepScout fetches the pages at a rate that the e-shop accepts. The usual times, with the wait in the queue, are:

  • setup: from a few minutes to 3 hours.

  • scraping: 1 to 2 hours for a few thousand products, several hours for 20,000, and up to 1 day for 100,000 or more.

  • matching: 1 hour for 1,000 products, 4 to 15 hours for 10,000, 1 to 2 days for 50,000.

  • EXPORTING, the last status: up to 1 hour. scrape_progress.percent and matching_progress.percent show the progress. matching_progress.estimated_minutes_left shows the time left. In the queue and in some phases, the progress does not change. A job without an error is not stuck: tell the user about a problem only if the job FAILED.

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": {
      "job_kind": "<job_kind>",
      "job_id": "<job_id>"
    },
    "name": "scout_get_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYes
job_kindYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnlyHint, openWorldHint), so the description carries the real burden and does: it explains the job lifecycle phases, expected durations per phase and per product volume, how progress fields behave, and that flat progress does not mean stuck. This is exactly the context an agent needs to avoid false failure reports.

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?

Front-loaded with the purpose and the polling rule, then a compact duration table that earns its space by setting wait expectations. The per-volume timing breakdown is slightly verbose but is the core guidance an agent needs, so it is not padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and annotations cover the safety profile; what remains is the timing and non-stuck semantics, which are handled thoroughly. The only gap is that neither job_id nor the job_kind-to-job correspondence is ever explained.

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 0%, so the description should compensate, and it only partially does. The phase list (setup, scraping, matching) implicitly maps to the job_kind enum, but job_id is never described and there is no statement that job_kind must correspond to the kind of job that was submitted.

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 ('Get the state of a job') and enumerates the returned facets (status, estimate, approval, settlement, error), which is far more than a restatement of the title. It implicitly separates itself from scout_list_jobs by being single-job detail, but it never names that sibling explicitly.

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 polling cadence (every 5-10 minutes) and an explicit termination condition (COMPLETED, FAILED, CANCELLED). It also gives a clear when-not rule: do not report a problem to the user unless the job actually FAILED, which heads off the main misuse pattern for a polling tool.

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

All DeepScout toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources