send_key

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

With no annotations, the description must disclose behavioral traits. It does not mention prerequisites (e.g., starting remote control), side effects on the session, error behavior, or whether it waits for a response. The action of sending a key is a state change, but the description leaves these aspects opaque.

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, front-loaded sentence that efficiently conveys the core function and examples. Every word adds value, with no wasted content.

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 the core purpose but omits important context such as how to target a non-default session, session lifecycle dependencies, and relationship to remote-control tools. Given the simple nature of the tool and no output schema, it is minimally adequate but has clear gaps in session handling and prerequisites.

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 low (33%), leaving the 'key' parameter without a description. The tool description compensates with examples of valid key names, which adds practical meaning. However, it does not clarify the session parameters (managedSession, deprecated tmuxSession) beyond the generic 'managed native Claude session,' so coverage remains incomplete.

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 clearly states the action ('Send') and the resource ('a single key name to the managed native Claude session'), with concrete examples (Enter, Escape, C-c, Up, Down). This distinguishes it from sibling tools like send_text, which sends text, making the purpose unambiguous.

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 gives clear context by specifying the target session and providing representative key examples, which imply when to use this tool (when sending key presses rather than text). However, it does not explicitly mention when to prefer alternatives (e.g., send_text) or exclude any scenarios, so it falls short of a 5.

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