Prompt a pane and read the reply

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does so effectively by revealing the separate Enter submission, the turn-aware wait logic (won't return on pre-prompt screen), and the triple gate (app toggle, HYPERPANES_ALLOW_INPUT=1, confirm=true). While it omits edge-case behaviors like timeout handling, the core operational nuances are well covered.

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 dense, three-sentence paragraph that front-loads the primary action, then explains wait behavior, then composition and requirements. Every sentence earns its place with no fluff, though a structured breakdown (e.g., bullets) could improve scannability. It's appropriately sized for the complexity.

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 composite tool with no output schema and no annotations, the description covers the essential aspects: purpose, relationship to sibling tools, wait semantics, and confirmation requirements. It lacks a detailed return format description, but that's not necessary given no output schema. The core functional contract is adequately conveyed.

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 high (86%), so the baseline is 3. The description adds semantic value for the `text` parameter (clean submission) and the `confirm` parameter (must be true as part of the triple gate), but it does not elaborate on parameters like `tail`, `owner`, `settleMs`, or `timeoutMs` beyond what the schema already specifies. It adds modest context without needing to fully compensate for schema gaps.

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 a specific action: 'Drive one full turn of a TUI agent ... with ONE call' and enumerates the exact sequence (type, submit, wait, return transcript and awaiting state). It also distinguishes this tool from siblings by explicitly naming its composition of send_input(submit) + read_pane(waitForIdle, mode:'screen'), making its unique role clear.

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 provides concrete usage context by explaining it composes send_input and read_pane, implying it should be used when a full send-and-read cycle is needed in one call. It gives an example use case (live `claude`) and notes the triple gate requirement, but it does not explicitly contrast with other sibling tools like send_message or provide when-not-to-use guidance.

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