start_process

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that processes can be long-running or interactive and run in different windows, but lacks critical details: whether this requires specific permissions, if processes persist across sessions, error handling, resource limits, or what happens on failure. For a process-starting tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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?

The description is appropriately sized and front-loaded: the first sentence states the core purpose, and the second adds crucial context about window targeting. Every sentence earns its place with no wasted words, making it efficient and easy to parse for an AI agent.

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?

Given the complexity of starting processes (which can involve permissions, resource management, and error handling), no annotations, no output schema, and only moderate schema coverage, the description is incomplete. It covers basic usage but misses behavioral aspects like what the tool returns, how to handle errors, or prerequisites. For a tool with siblings like 'stop_process' and 'send_input', more context on integration would be helpful.

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?

Schema description coverage is 67% (2 out of 3 parameters have descriptions). The description adds some value by explaining the 'target_window' parameter's purpose ('ui' for interactive apps, 'exec' for background processes), which complements the schema's example. However, it doesn't provide additional meaning for 'command' or 'workspace_id' beyond what the schema offers, and with moderate coverage, the description only partially compensates.

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?

The description clearly states the tool's purpose: 'Start a long-running or interactive process.' It specifies the verb ('Start') and resource ('process'), and distinguishes it from siblings like 'execute_command' by mentioning long-running/interactive nature and window targeting. However, it doesn't explicitly differentiate from 'stop_process' or 'send_input' in terms of process lifecycle management.

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?

The description provides clear context for when to use this tool: for long-running or interactive processes, with guidance on window selection ('ui' for interactive apps, 'exec' for background). It implies alternatives by mentioning defaults and use cases, but doesn't explicitly name when to use 'execute_command' instead or other siblings like 'stop_process' for termination.

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