terminal_send

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

With no annotations provided, the description carries the full burden and excels at it. It discloses fixed execution order, no deduplication, that text bypasses argv and error messages, that the server does not log or echo input, and that tmux pipe-pane still records raw pane output. This is unusually transparent for a side-effecting tool.

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 long but dense, with no filler. It front-loads the primary purpose and then adds necessary behavioral, ordering, and logging caveats. Every sentence 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?

The description covers prerequisites, ordering, logging, and privacy nuances almost completely. The only notable gap is return-value semantics: there is no output schema, and the description references 'tool result' only in passing without explaining what the agent receives on success.

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 0%, but the description compensates fully by explaining the semantics of device, text, keys, and enter, including ordering and the duplicate-Enter edge case. It adds meaning well beyond the bare parameter names in the input schema.

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 states a specific verb and resource ('Send input to a device's open terminal session') and clearly differentiates the tool from siblings such as terminal_read, terminal_list, and terminal_open by focusing on sending input. It also narrows the scope to open sessions within the active topology.

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?

It provides strong operational context: the device must still be present in the active topology and the session is reloaded from disk on every call. However, it does not explicitly name sibling alternatives or state when not to use this tool, so the guidance is clear but not fully explicit.

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