chatgpt_send_message

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

With no annotations, the description carries the burden of behavioral disclosure. It usefully reveals that Pro or model names containing Pro trigger unlimited waiting, normal tiers use timeoutMs, and files are only passed on explicit user request. It does not disclose side effects of creating/continuing chats, how the final answer is returned, or potential failure/reconciliation behavior.

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 reasonably compact for an 11-parameter combined tool, using three short sentences. Key behavioral notes about Pro/wait and file handling are front-loaded after the capability list. The first sentence is a long enumeration, but it is still readable and every sentence contributes useful 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?

For such a complex tool with no annotations and no output schema, the description is serviceable but incomplete. It covers the main task surface and the most important behavioral caveats, but it does not describe the returned answer structure, how operationId should be used, or how this tool relates to the many single-purpose siblings. An agent could invoke it correctly in common cases, but edge cases and alternative routing are left to inference.

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?

Input schema coverage is only 18%, so the description must compensate. It names several parameters at a high level and adds meaningful semantics for answerTier/model ('Pro' causes infinite waiting) and files (only when explicitly requested). It does not clarify the operationId reconciliation behavior in the description, though the schema provides a partial Vietnamese description, and several optional parameters remain minimally explained.

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 this as a combined tool for creating or continuing a chat, selecting mode/model/thinking level/tier, switching temporary chat, uploading files, writing a prompt, sending, and getting an answer. This goes well beyond the tool name and makes the broad scope apparent. However, it does not explicitly contrast itself with its many sibling tools, so it stops short of full differentiation.

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 concrete usage guidance for files ('only pass files when the user explicitly asks to upload') and for timeout behavior with Pro tiers. It does not, however, state when to use this combined tool versus the individual sibling tools such as chatgpt_select_mode, chatgpt_write_prompt, or chatgpt_submit_prompt. The usage context is implied by the word '组合工具' but not made explicit.

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