ask

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

Discloses injection into running terminal and reading from transcript. No annotations provided, so description carries full burden; side effect of interruption is noted.

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?

Three sentences cover purpose, mechanism, and constraint without redundancy. Front-loaded with primary action.

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?

Adequately describes behavior and prerequisites but lacks explicit return value format or error handling (e.g., timeout, non-live session). No output schema to compensate.

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 already covers 100% of parameters with descriptions. Description adds no new semantic details beyond the mechanism of injection/reading.

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?

Clearly states the tool asks a LIVE session a question, injects into terminal, reads answer. Distinct from siblings like list_sessions (listing) and send_message (sending messages).

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?

Explicitly states only works on live sessions (from list_sessions) and warns about interrupting the target. Lacks explicit alternatives for non-live sessions but context is clear.

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