chatgpt_send_message

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

With no annotations, the description discloses important behavioral traits: Pro tier or model names containing 'Pro' trigger infinite waiting, normal tiers use timeoutMs, and files are only sent when explicitly requested. It also reveals that the tool can start or continue conversations. It omits return format and failure modes, but the added details are meaningful.

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?

Three sentences, front-loaded with the composite-tool claim, followed by a concise capability list and two critical behavioral caveats. Every clause earns its place; no redundant wording.

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 10 parameters and no output schema, the description covers core parameter semantics and key behaviors, but it omits the structure of the returned answer, the exact effect of wait=false, prerequisites, and error/edge cases. It is adequate for basic usage but not fully complete for a complex composite tool.

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 only 10%, so the description carries the burden of explaining parameters. It successfully maps mode, model, thinkingLevel, answerTier, temporary, newChat, prompt, files, and timeoutMs through the capability list and the Pro/timeout/files caveats. The 'wait' parameter remains under-explained, but overall the description adds substantial semantic context.

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 opens with '组合工具' (composite tool) and lists a full range of capabilities: new/continue chat, mode/model/thinking/tier selection, temporary chat, file upload, prompt writing, sending and receiving answers. This clearly specifies the tool's scope and distinguishes it from the granular sibling tools.

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 '组合工具' label implies this is the one-stop tool, and the listed capabilities provide context, but the description never explicitly states when to use this versus the individual chatgpt_* sibling tools, nor does it give exclusions or alternative routes. Guidance is implied, not explicit.

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