Send Control Character

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

Annotations only signal a non-read-only, non-idempotent mutation, so the description carries the behavioral burden. It discloses safety boundaries ('physically cannot reach any other process', 'no keyboard/focus involved'), transport limitations ('Ctrl+Break is not supported'), and platform-specific caveats (PowerShell line editor behavior). No contradiction with annotations.

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 main purpose is front-loaded in the first sentence, followed by concise safety rationale, args, limitations, and reliability guidance. Each paragraph adds distinct value, and the structure is easy to scan without padding.

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 2-parameter tool with no output schema, the description thoroughly covers purpose, behavior, limitations, and alternatives. The only notable gap is that it never explicitly states that the target session must already be open (implied by sibling open_terminal_session), nor what happens if an invalid session ID is provided.

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 the baseline is 3. The description adds meaning beyond the schema by clarifying that 'key' is a single letter for Ctrl+<key>, that 'C' is for interrupt, and that Ctrl+Break is not representable over this transport. The 'session' parameter is not expanded, but the added key semantics justify a 4.

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 opens with a specific verb and resource: 'Sends a real Ctrl+<key> control byte ... directly into a session's own shell input.' It also distinguishes itself from the sibling write_to_terminal by emphasizing it writes a literal ASCII control byte into the input pipe, not keyboard simulation or regular text.

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 explicit when-to-use guidance ('Reliably interrupts a command that is actually running', 'Use "C" to interrupt a running command') and when-not-to-use guidance ('not a reliable way to cancel text already typed into the prompt...'). It also gives an alternative action: 'To discard an unsent fragment, close and reopen the session instead.'

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