submit_prompt

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It mentions 'safer chunked input' and the return value, but omits critical aspects such as preflight blocking (e.g., busy/non-idle captures), the force bypass, retry behavior, and the fact that it sends keystrokes to a terminal. These are significant behavioral details that an agent needs to safely invoke the tool.

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 two sentences long, with the action front-loaded and no filler. Every clause contributes meaning, and the key return behavior is stated efficiently. It is a model of concision.

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?

This is a complex 10-parameter mutation tool with no annotations and no output schema. The description only provides the high-level purpose and a single return detail (waitAfterCursor), but it lacks context on preflight blocks, retry mechanics, session management, and parameter relationships. It is not sufficient for an agent to use the tool effectively and safely without additional information.

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 about 50%, but the tool description adds no explanation for parameters like lines, chunkSize, chunkDelayMs, managedSession, or tmuxSession. The mention of 'chunked input' hints at chunking-related params but does not clarify their values or how they interact. The description fails to compensate for the undocumented parameters.

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 what the tool does: 'Paste and submit a complete prompt to Claude using safer chunked input.' It specifies the resource ('a complete prompt'), the action ('paste and submit'), and the method ('chunked input'), and it distinguishes the tool from siblings like send_text/send_key by noting the return of waitAfterCursor for wait_for_claude_turn.

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 describes the primary use case (submitting a complete prompt) and signals the intended workflow by stating it returns a waitAfterCursor for wait_for_claude_turn. While it doesn't explicitly compare with alternatives like send_text, the phrase 'complete prompt' and 'chunked input' imply when this tool is appropriate, providing clear context if not explicit exclusions.

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