BCD — Bridge Control Delegate

app_press

Destructive

Press an element of the latest app_snapshot, as clicking it does: a button, menu item, link or checkbox. A press can send, delete or quit, as in the app itself; after a menu command the state is the front window. 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>"
    },
    "name": "app_press"
  }
}

Input Schema

Name	Required	Description
`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

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (destructiveHint=true is consistent with 'a press can send, delete or quit'). It discloses the commit/abort semantics of a stale snapshot, that the error carries the current state to retry from, that the return value includes the next snapshotId so no extra snapshot is needed, that success of the send is not proof of task success, and that operating apps can run programs.

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 its meaning, then layered with failure modes and permissions; every sentence carries distinct information. It is dense and some clauses (e.g. 'after a menu command the state is the front window') take a re-read, costing a little clarity.

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, the description still explains the return value (new app state plus next snapshotId) and the error shape (current state for retry). Combined with permission and staleness rules, an agent has everything needed to call it and recover from failure.

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 60% and elementId/snapshotId have no schema description, but the prose supplies their relationship: the element comes from the snapshot identified by snapshotId, and the returned next snapshotId is what a follow-up call should use. It does not explain elementId's 1–600 index range or when takeOver applies beyond the schema's own text.

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 (press) on a specific resource (an element of the latest app_snapshot) and enumerates what that means: button, menu item, link or checkbox. It is clearly distinct from siblings like app_select, app_type, app_show_menu and app_increment.

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 clear preconditions — the press operates on the latest snapshot, and it is refused if the window changed or a person used keyboard/mouse since the snapshot — plus a permission requirement. It does not explicitly name alternatives (e.g., use app_show_menu for menu traversal or app_type for text entry), so the when-to-use-vs-sibling guidance is implicit rather than stated.

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?