send_control

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

The annotations already declare destructiveHint=true and idempotentHint=false, so the agent knows this is a non-idempotent, potentially destructive action. The description adds the useful scoping that the control must be 'explicit reviewed,' but it does not explain side effects of ENTER, INTERRUPT, or ESCAPE, or what happens after the control is sent.

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 a single focused sentence of about ten words with no filler. It places the core action and object first, and every word contributes either to scope ('one explicit reviewed') or to target ('existing channel').

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?

With only two parameters and an output schema absent, the description plus schema is sufficient to understand the basic call shape. However, it does not describe the expected return value, failure modes, or behavioral consequences of each control, which an agent would need for confident invocation in a terminal-control context.

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 schema documents channel_id as coming from list_channels, and control has a clear enum. The description adds the semantic framing 'terminal control' and the 'reviewed' constraint, but it does not clarify what each enum value does or the practical difference between INTERRUPT and ESCAPE, leaving part of the burden on the agent.

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 ('Send'), a concrete resource ('terminal control'), and a target ('existing channel'). It is clearly distinct from the sibling write_text, which sends textual content rather than control signals, though it does not explicitly name that sibling.

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 phrase 'to an existing channel' implies a precondition and suggests this tool is for control actions rather than text or read operations. However, there is no explicit guidance about when to choose send_control over write_text or read_channel, and no mention that channels should be obtained via list_channels first.

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