以無痕聊天送出提示

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

With no annotations to lean on, the description carries the full burden and does so well: every call opens a brand-new chat, prompts are not persisted to account history, provider-specific auth requirements, and named failure modes (logged_out, thinking_not_found). It also notes that prompts are typed verbatim, including multi-line text.

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?

Front-loads the core action and the fresh-chat guarantee, then layers auth and ordering details. Dense but every sentence earns its place; slightly long, though nothing is redundant.

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?

No output schema exists, and the description compensates by stating it returns the answer text. Combined with auth requirements, error labels, and model/thinking sequencing, an agent has everything needed to invoke this correctly.

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 100%, so parameters are already documented; the description adds value by revealing the ordering dependency between model and thinking (depths depend on the model) and clarifying that gemini's thinking labels are on/off toggles that get switched on. It does not add much about timeout_seconds beyond the schema.

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?

States a specific verb and resource ('Send a prompt through a fresh private/temporary chat of the chosen service') plus what is returned ('the answer text'). It is immediately distinguishable from siblings like webchat_models and webchat_login, which it references by name.

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?

Gives explicit when-to-use conditions and prerequisites: works logged-out (guest) on chatgpt and gemini, while claude and grok require webchat_login, and a guest hitting those gets a logged_out error. It also prescribes sequencing ('pick thinking after model') and points to webchat_models for valid labels.

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