Window: run a command

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

With no annotations, the description carries the burden well: it discloses that commands never open a dialog (no interactive fallback), that new spaces/tabs are immediately visible side effects, and that the call returns created IDs. It stops short of error/failure behavior or permission requirements.

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?

A single dense paragraph with the verb and command examples front-loaded, followed by behavioral caveats. Every clause carries information, though the packed command list makes it slightly hard to scan and the '...' elision forces a lookup elsewhere.

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 polymorphic dispatcher with a free-form args object and no output schema, the description supplies return semantics (created IDs), side-effect visibility, and partial per-command argument contracts with a pointer to herdr_app_commands for the rest. Only the unenumerated commands and error cases are left undocumented.

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 coverage is 100%, so baseline would be 3, but the description goes further by spelling out the concrete key sets for individual commands (space.new {name, folder, machine, argv, task}, pane.split {direction, pane}), which the free-form `args` object in the schema cannot convey on its own.

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 (run) and resource (window command), then enumerates concrete command names with their argument shapes. It also distinguishes itself from herdr_app_commands, which only lists the commands, and from herdr_exec/herdr_run by scoping to window/app commands.

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?

Explicit invocation guidance: 'Supply every required argument: commands from an agent never open a dialog,' plus a clear constraint that new spaces/tabs appear immediately and should only be created when the user asks, with explicit names. It points to herdr_app_commands for discovery, though it doesn't contrast against herdr_exec or herdr_run directly.

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