Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Get a homework job

homework_get
Read-only

One job whole: what to do (steps), each item with its ref, words, picture addresses, poll options and the time it should go out, and its state. A photos job has one item per real place or thing: what it is, where, how many pictures wait for it and where Marsell already looked. A job's steps say which steps stay the owner's (on a Google Ads account: adding the payment method and pressing Connect Google Ads); leave those to them. Do the job in the owner's name as the steps say, then report it with homework_done.

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_id": "<job_id>"
    },
    "name": "homework_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYesThe job's id from homework_list (hw- and 16 hex characters).
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: the shape of the result for normal vs photos jobs, the rule that some steps belong to the owner and must be left alone, and the required follow-up call to homework_done.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is front-loaded with the return shape and does not pad with filler, but the prose is a rambling run-on with awkward internal references ('Marsell already looked', 'picture addresses') that cost clarity without earning extra meaning.

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?

No output schema exists, so the description carries the burden of explaining return values — and it does so for both normal and photos jobs, plus the workflow that follows. It is nearly complete, with only error/missing-job behavior and pagination-style concerns absent.

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 coverage is 100%, so job_id's format (hw- plus 16 hex characters) and project's optionality are already documented in the schema. The description adds nothing about either parameter, so the baseline 3 applies.

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 conveys that this returns a single complete job — its steps, per-item refs, words, picture addresses, poll options, send time, and state. It is specific about the resource but opens with the vague fragment 'One job whole' rather than a clean verb, and never explicitly contrasts itself with homework_list beyond noting the id origin.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the workflow: get the job, respect owner-only steps, then report with homework_done. However, it never states when to call this versus homework_list or what to do if the job is missing, so the guidance is embedded rather than explicit.

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

All Marsell 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