viaSocket

run_app_action

Destructive

Do one thing in the user's app right now, on their own account: send an email, post a message, add a row, create a record, fetch data. Body { service_id, action_id, auth_id, instructions, thread_id }: service_id from search_apps, action_id from list_app_actions, auth_id from list_connections, instructions in plain words carrying every value (recipient, subject, body, sheet name…), thread_id an id you make up and reuse for retries of the same request. viaSocket's builder turns the instructions into the action's input and runs it; the reply is the app's own result. It acts for real, so say exactly what it will do (which account, which action, which values) and get the user's yes first. For something that should happen repeatedly ("every time", "every morning"), build an automation instead, as the skill describes.

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": "run_app_action"
  }
}

Input Schema

Name	Required	Description
`auth_id`	No	e.g. authAbC123xyz
`action_id`	No	e.g. row1jrbor
`thread_id`	No	e.g. slack-send-message-sales
`service_id`	No	e.g. rowbu58rc
`instructions`	No	e.g. List the channels in the workspace

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, but the description adds real value on top: it acts for real, the agent must state exactly which account/action/values and obtain the user's yes first, and the reply is the app's own result. The thread_id retry note implies non-idempotency in a useful way. It stops short of describing failure modes or partial-execution behavior.

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 action and examples, then the body contract, then the confirmation requirement, then the alternative. Dense but nearly every clause carries information; the parenthetical value list and the trailing 'as the skill describes' are the only mildly loose elements.

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 destructive, open-world, no-output-schema tool this covers the essentials: what it does, where each id comes from, how instructions are interpreted, what comes back, and that consent is required. Error and partial-failure handling are the main omissions.

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% but the schema descriptions are only bare examples ('e.g. rowbu58rc'), so the description carries real weight by giving provenance for three params (search_apps, list_app_actions, list_connections) and by explaining that instructions must carry every literal value (recipient, subject, body, sheet name). It does not clarify that the schema marks zero required parameters, which is a gap.

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?

States a specific verb and resource ('Do one thing in the user's app right now, on their own account') and enumerates concrete outcomes (send an email, post a message, add a row, create a record, fetch data). This clearly separates it from sibling metadata tools like list_app_actions or search_apps, which only discover the ids this tool consumes.

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?

Explicitly names the exclusion: for recurring work ('every time', 'every morning') build an automation instead. It also routes the agent to the three discovery siblings that supply service_id, action_id and auth_id, so the when-and-how of invocation is fully covered.

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

All viaSocket tools Inspect

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

Need Help?