prompt_agent

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

No annotations are provided, so the description carries the full behavioral burden. It explains that the tool types and submits text, optionally waits for the agent to settle, and fails if nothing matches within the timeout. It does not cover side effects or preconditions like whether the agent pane needs focus, but the disclosed behavior is substantial.

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 front-loaded with the core action, then uses a compact parameter-list format. Every sentence adds information and there is no repeated schema information.

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?

Given four parameters, no annotations, and no schema descriptions, the description explains the key semantics and failure behavior well enough to invoke the tool correctly. Minor gaps remain around explicit differentiation from sibling tools and any requirements like active pane or agent ordering, but the core usage is complete.

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 0%, and the description compensates fully. It explains `target` with examples, `wait` with a concrete definition of settled states, and `timeout_ms` with its caveat that it is only used when `wait=True`. Even `text` is clarified as the prompt being submitted.

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 ('submit a prompt') and the resource ('an agent pane'), and clarifies the mechanism ('types the text and submits it'). This distinguishes it from sibling tools like send_text or send_keys, which only send keystrokes without submitting.

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 targeting context: pane IDs like `w17:p1` or agent names, and points to `list_agents` for discovery. It also explains when `wait` and `timeout_ms` matter. However, it does not explicitly say when to prefer this over siblings like `wait_agent` or `send_text`.

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