Skip to main content
Glama

desktop_key_down

Holds a keyboard key or modifier down for sustained shortcuts or input; stateless sessions reject it by design, so use press for one-shot key actions.

Instructions

agent-desktop key-down: Hold a key or modifier down (fails closed in stateless mode; use press)

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": {
      "combo": "<combo>"
    },
    "name": "desktop_key_down"
  }
}

Input Schema

NameRequiredDescriptionDefault
comboYesKey or modifier to hold/release: shift, meta, ctrl ... (cmd is accepted); the command is rejected in stateless mode, use press instead
forceNoSend the combo even if the adapter flags it as a dangerous shortcut

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose one important trait — fail-closed behavior in stateless mode — plus the dangerous-shortcut override implied by the force parameter, but it never says how long a hold persists, what state it leaves behind, what error shape a rejection takes, or that a paired key_up is required to release.

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?

One compact sentence with the failure mode front-loaded right after the action, and no filler. The only waste is the redundant 'agent-desktop key-down:' prefix, which duplicates the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, no-annotation, no-output-schema tool, the description covers the action and the stateless failure mode but omits release semantics and side effects on host state. An agent can call it correctly in isolation but may not know it must later release the key.

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 100%, so both combo and force are already documented in the input schema, including the cmd alias and the stateless rejection. The description adds no syntax, accepted modifier list, or formatting guidance beyond what the schema states, so the baseline of 3 applies.

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?

The description names a specific action and resource: 'Hold a key or modifier down,' which is concrete enough to distinguish it from press-style or release-style operations. The 'agent-desktop key-down:' prefix merely restates the tool name and adds nothing, and the natural counterpart (desktop_key_up) is never named, so the pairing is only inferable.

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?

It gives an explicit negative condition and a redirect: 'fails closed in stateless mode; use press' — that is a real when-not rule with a named alternative. It stops short of stating the obvious counterpart behavior (that a hold must be followed by a key_up), so the lifecycle guidance is incomplete.

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