start_new_conversation

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

With no annotations, the description carries the full burden. It clearly discloses read-only sandbox mode, inability to modify files/execute commands, and returns a thread_id and response. The description adds context beyond the basic schema, though it omits potential auth/error details.

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 well-structured with clear sections (main description, limitations, when to use, args, returns). It is front-loaded with the core purpose, and every bullet point adds value without excessive verbosity.

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?

Despite no output schema or annotations, the description explains the return format (Dict with thread_id and response), lists limitations, and provides use cases. It is sufficiently complete for an AI agent to understand when and how to invoke the 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 description coverage is 0%, but the description compensates by explaining each parameter: prompt includes the useful '@filepath' syntax hint, and working_directory is described as 'Directory path for codex to work in.' This adds meaning 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?

The description states a specific verb and resource: 'Start a new conversation with OpenAI Codex CLI.' It clearly distinguishes from the sibling tool continue_conversation by mentioning it returns a thread_id for continuing the conversation later.

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?

Provides explicit 'When to use' list with four concrete use cases and a 'Limitations' section that explicitly excludes write operations and shell commands, saying 'Use only for read-only tasks.' This is strong guidance on when to use and when not to use.

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