Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Agents read

agents_read
Read-only

Reads every agent that works on this business at once, for a question about all of them (one agent: agent_open alone), read now: what each does, its rhythm, what its switch does and where it stands, when it last ran and runs next, what its last run found, the cards it has waiting for the owner, where its work shows in the app, and where the owner starts one that waits for their press; also the agents that do not fit this business.

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": "agents_read"
  }
}

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 declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine value by enumerating what comes back (purpose, rhythm, switch state, last/next run, last findings, waiting cards, app placement) and notes it also returns agents outside this business. It omits pagination/auth/volume behavior, but for a read tool that is minor.

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?

Purpose is front-loaded, but the remainder is a single sprawling run-on sentence joined by commas and semicolons, with awkward phrasing like 'read now:' and 'one that waits for their press.' The content is useful but hard to parse; it would benefit from being broken into clauses.

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 what is returned, and it does so with a detailed enumeration of fields and states. Combined with read-only annotations, an agent has enough to decide and call it; only structural detail of the return shape is missing.

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?

Only one optional parameter ('project') with 100% schema description coverage, so the schema already does the work. The description implies scoping to 'this business' but adds no detail about the project identifier beyond the schema.

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?

States a specific verb and resource: 'Reads every agent that works on this business at once.' It explicitly distinguishes itself from the sibling agent_open ('one agent: agent_open alone'), so an agent can route correctly without opening the schema.

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?

Gives a clear selection condition ('for a question about all of them') and names the alternative for the single-agent case. It stops short of other exclusions, but the primary fork is 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