chatgpt_submit_prompt

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

With no annotations, the description must carry the behavioral disclosure burden. It usefully reveals a key behavior: automatic infinite waiting for Pro tiers and Pro-named models, with timeoutMs only for normal tiers. But it does not disclose what happens on timeout, what the return value is, whether wait=false bypasses waiting entirely, or any side effects beyond sending the prompt.

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 compact: two short sentences, with the primary action front-loaded and the timeout qualifier placed as a natural follow-up. Every clause contributes useful information, and there is no repetition of schema fields or tool title.

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 tool with no annotations, no output schema, and three optional parameters, the description gives a workable high-level understanding but omits important operational details such as return values, timeout failure behavior, duplicate-submission protection via operationId, and how this step fits with siblings like chatgpt_get_latest_response.

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 only 33%, so the description must compensate. It adds meaningful context for timeoutMs ('timeoutMs 仅用于普通档位') and loosely ties '等待' to the wait parameter. However, the wait parameter's false-case behavior is not explained, and operationId semantics are left to the schema's Vietnamese description rather than the main description.

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 identifies the action: '发送当前输入框中的提示词' (submit the prompt in the current input box) and adds the waiting-for-completion behavior. It is specific and actionable, but it does not distinguish itself from sibling tools like chatgpt_send_message or chatgpt_write_prompt, so it does not fully earn a 5.

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 implies the tool is used after a prompt is already in the input box and that waiting is configurable. It also gives a conditional usage detail: Pro tier or Pro-named models wait indefinitely, while timeoutMs applies only to normal tiers. However, there is no explicit guidance about when to choose this tool over alternatives such as chatgpt_send_message.

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