BCD — Bridge Control Delegate

app_type

Destructive

Replace the text of a text field of the latest app_snapshot with text (never a password field). Some apps do not count typed text as an edit, so save explicitly. Returns the app's new state with the next snapshotId, so no extra snapshot is needed. If the window changed, or a person used the keyboard or mouse in the app since the snapshot, nothing is done and the error comes with the current state to retry from. A sent action is not proof the task succeeded. Needs ui and process permission (operating apps can run programs).

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": {
      "snapshotId": "<snapshotId>",
      "elementId": "<elementId>",
      "text": "<text>"
    },
    "name": "app_type"
  }
}

Input Schema

Name	Required	Description
`text`	Yes
`deviceId`	No	Computer name or id from list_devices. Optional with one computer online or a default set.
`takeOver`	No	Only when the user says so: act even though another conversation is operating this screen, which then holds it no longer.
`elementId`	Yes
`snapshotId`	Yes
`workSessionId`	No	Work session from create_work_session. Pass the same ID on every call in this conversation; omit for legacy unscoped work.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

addedInput schema / properties / takeOver

Added value: +{
+  "description": "Only when the user says so: act even though another conversation is operating this screen, which then holds it no longer.",
+  "type": "boolean"
+}

AddedOct 8, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: names the password-field exclusion, the caveat that typing may not count as an edit, the concurrency staleness rule (window change or human input aborts with current state to retry from), the warning that a sent action is not proof of success, and the required ui/process permissions.

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-loads the core action and constraints with no filler; each sentence carries distinct information. Slightly dense across many clauses, but nothing is wasted.

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?

For a destructive mutation with no output schema, it covers return value (new app state plus next snapshotId so no extra snapshot is needed), permission requirements, staleness/retry behavior, and the success-verification caveat. An agent has everything needed to call and interpret it.

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 50%; deviceId, takeOver and workSessionId are documented in the schema itself. The description clarifies snapshotId as the latest app_snapshot and text as the replacement value, but leaves elementId and the device/session semantics unelaborated, which is baseline-appropriate rather than additive.

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 (replace) and resource (text field of the latest app_snapshot), plus a scope exclusion (never a password field). An agent can distinguish it from siblings like app_press or app_increment directly from the description.

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 real operating context: some apps don't register typed text so save explicitly, and the call is a no-op with retry state if the window changed or a person used input. It does not name an alternative sibling for other kinds of interaction, so it falls short of a full when/when-not routing statement.

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

All BCD — Bridge Control Delegate 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?