Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Attachment watch

attachment_watch

Describes a video the owner sent: what happens, who and what is on screen, the words on it, what is said, the sound and how it is shot. It spends tokens, so first call it with go false for its price and tell the owner; call it with go true only on their yes, or when they asked for it with that price already said. Its id comes from input.attached or attachment_read. It needs an act key, and spends the owner's tokens as the chat's same tool would: say the price before you spend.

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": {
      "id": "<id>",
      "go": "<go>"
    },
    "name": "attachment_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
goYesfalse: only the price, nothing spent; true: describe it now, which spends tokens
idYesthe video's id
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

The annotations mark this as not read-only and not destructive but do not explain token spend or consent requirements. The description fills that gap by warning that it spends the owner's tokens, requiring an act key, and mandating that the price be stated before spending.

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 purpose is front-loaded and the key operational rule is stated clearly. There is some redundancy: the token-spend warning appears both in the second sentence and the final sentence, and the phrasing is awkward in places.

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?

For a tool with no output schema and full schema coverage, the description covers the critical missing context: cost, consent, id source, and act key. It could say more about the return shape or the optional project parameter, but the essentials for correct invocation are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds useful meaning beyond the schema: it explains the go=false/go=true consent workflow and tells the agent that the video id comes from input.attached or attachment_read. It does not add much about the optional project parameter.

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 states a specific verb and resource: it describes a video the owner sent, including what happens, who/what is on screen, words, speech, sound, and shooting style. This is clear enough to distinguish it from attachment_read, which is mentioned only as a source of the video id.

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?

It gives explicit when-to-use guidance: call with go false first to get the price and tell the owner, then call with go true only after the owner agrees or has already accepted that price. It also explains where the id comes from, leaving little ambiguity about when and how to invoke it.

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