opencode_send

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

No annotations exist, so the description carries the burden. It discloses the supported key set and implies raw passthrough, but doesn't state side effects like whether output is appended asynchronously, whether input is echoed, or whether there's a risk to running processes. The '<enter>'/'<ctrl-c>' examples hint at interaction but lack contextual depth.

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 concise sentence effectively communicates the core behavior, followed by a compact list of supported special keys. No waste, but slightly more context could be included without bloating.

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 an interactive PTY-send tool with no annotations and no output schema, the description covers the essential action and key support. However, it doesn't explain return/output behavior, whether keys are case-sensitive or escaped, or what happens if no session is active. Adequate but with gaps for a tool that writes to a live process.

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%, with both parameters described. The description adds the key-sequence syntax concept ('yes<enter>', '<ctrl-c>'), which complements rather than repeats the schema. Baseline 3 is appropriate given full schema coverage and light added semantics.

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 clear verb+resource ('Sends raw text or keystrokes to the PTY') and lists supported special keys. It distinguishes intent from siblings like opencode_command and opencode_interrupt, though it doesn't explicitly contrast against them.

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 implies a clear usage (sending input to a running PTY process) and gives supported key syntax as examples in the schema. However, it doesn't explicitly state when to use this vs alternatives like opencode_command or opencode_interrupt, nor when it should NOT be used.

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