Starts the DOSBox binary named in the config file using an isolated config directory, attaches to the spawned instance, and refuses if one is already managed.
Spawn the dosbox binary named in the human-edited config file (with an isolated config dir) and attach to it. Refuses while an instance is already managed.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only supply readOnlyHint=false, so the description carries most of the burden and does so well: it discloses that the process is spawned from a human-edited config file, run with an isolated config dir, that it attaches afterward, and that it refuses when an instance is already managed. It stops short of describing failure modes beyond the busy case or what a successful spawn yields (PID, session id).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no filler; the core action and the config-dir detail come first, and the refusal precondition lands last as a guard. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a no-parameter lifecycle tool with a thin annotation set and no output schema, the description covers the essential behavior and the key precondition. Remaining gaps — what is returned on success and the behavior on partial failure — are modest given the absent output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, which sets the baseline at 4. The description correctly implies the binary/configuration comes from a human-edited config file rather than any argument, so an agent is not left hunting for a missing path parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Spawn') and resource ('the dosbox binary named in the human-edited config file') plus the follow-on action ('attach to it'), so an agent knows this launches and binds to a new DOSBox instance rather than connecting to an existing one. It does not explicitly name the sibling it contrasts with (bridge_connect), which keeps it short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides one hard precondition — 'Refuses while an instance is already managed' — which tells the agent when the call will fail. However, it never names the alternative to use instead (bridge_connect / bridge_stop) or when to prefer starting a fresh instance over attaching, so usage is implied rather than directed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.