Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

List the homework

homework_list
Read-only

The jobs Marsell saved for you, the owner's own AI: work that needs the owner's own logins, files or inbox, such as YouTube posts and polls that no app can post, or real photos of a place Marsell found none of, from the owner's own files, or setting up a Google Ads account with the owner when they pressed Give it to your AI on Sell › Ads. Soonest due first, with each job's state: proposed (waiting for the owner's yes on its card, so not yet yours to take), waiting, taken, done or stuck. Check it whenever the owner asks you to check Marsell, and each time your own timer wakes you. While homework is on and no timer of yours is on file (or yours stopped), the answer says to ask the owner about a pulling schedule (ask_the_owner) and gives the prompt your timer runs (timer_prompt). While the card that asks who Marsell may talk to for them waits (reach_card), ask_the_owner also says to tell the owner where it is: only they answer it, in Marsell. Reads only.

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": "homework_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
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

A3.8/5.0
Behavior4/5

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

Annotations already cover the read-only, non-destructive profile, and the description adds real behavioral detail on top: ordering ('Soonest due first'), the meaning of each state (proposed is 'not yet yours to take'), and conditional response content (ask_the_owner, timer_prompt, reach_card guidance). It does not discuss pagination or result size limits, which is the main remaining gap.

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

Conciseness2/5

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

The description is front-loaded with a usable first clause, but it is a sprawling run-on with deeply nested relative clauses, especially the sentence about reach_card and ask_the_owner, which is hard to parse in one pass. Several embedded instructions about timers and cards arguably belong to behavior of other tools.

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 and a single trivial parameter, the description carries the burden of explaining returns, and it does: ordered list, state vocabulary, and the conditional fields returned when no timer is on file. An agent has enough to call it and interpret the response without guessing.

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% for the single optional `project` parameter, so the schema carries parameter meaning. The description never mentions `project` at all, so it adds nothing beyond the structured field; a 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 states a specific resource — the jobs Marsell saved for the owner's AI — and defines them concretely (owner-login/file/inbox work like YouTube posts, polls, photos, Ads setup). It is clear this lists items with their states, but it never names the natural alternatives such as homework_get or work_list, so sibling differentiation is left implicit.

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

Usage Guidelines4/5

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

It gives explicit trigger conditions: 'whenever the owner asks you to check Marsell' and 'each time your own timer wakes you.' What it omits is a negative case — nothing says when to use homework_get or work_list instead of this list.

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