ask_chatgpt

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

Annotations are minimal (readOnly false, openWorld true, destructive false), so the description adds meaningful context: Chrome starts with a saved login, session_id restores/continues chats, project_url overrides the default project, and timeout is bounded at 1–840 seconds. It does not contradict annotations and adds behavioral detail beyond them.

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 three compact sentences with no filler. It front-loads the core action, then efficiently covers effort selection, session handling, project override, and timeout.

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 five parameters and no output schema, the description covers invocation, effort choices, session lifecycle, project selection, authentication context, and timeout. The main gap is that it does not describe the return value or response format, and it does not mention the relationship to read_chatgpt.

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 0%, but the description compensates comprehensively: it explains effort options, session_id semantics, project_url behavior, and the timeout range. Even though 'prompt' is not explicitly described, it is clearly implied by 'Send one task'.

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 the action as 'Send one task and wait', naming a specific verb and resource (ChatGPT). It does not explicitly distinguish itself from the sibling tool read_chatgpt, so it misses the full differentiation criterion.

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 provides practical usage guidance: when to choose instant/medium/high vs pro effort, how to start a new chat, how to continue one with session_id, and how to override the project with project_url. It does not explicitly state when to use this tool instead of read_chatgpt, so it lacks explicit exclusions.

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