Start a new T3 thread

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

With no annotations provided, the description carries the full transparency burden. It discloses key behavioral traits: the thread runs in the project workspace (no worktree isolation), model selection defaults, and runtimeMode defaults to 'approval-required' (safest) with a recommendation for 'full-access' for autonomous work. This goes beyond schema details by explaining the default behavior and safety posture, though it does not explicitly mention side effects like agent autonomy or asynchronous execution.

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 dense sentences with no wasted words. The first sentence states the primary purpose, the second adds a workspace-specific constraint, and the third covers default behaviors. Each sentence earns its place and the most critical information (what it does) is front-loaded.

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 the tool's complexity (7 params, creates asynchronous work), the description covers the essential launch context: project/thread creation, first message, default model, runtime mode options, and the workspace isolation limitation. It does not describe the return value or how to monitor the resulting thread, but with no output schema and sibling tools like thread_digest and wait_for_change, this is a reasonable gap. Overall, it is complete enough for an agent to successfully 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 coverage is high (86%), so the baseline is 3. The description adds value by explaining the model fallback chain ('defaults to project's default, falling back to most recent thread's model') and the runtimeMode default semantics (approval-required safest, full-access for autonomous). This enriches the schema's bare enumerations and clarifies the actual behavior for model and runtimeMode.

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 tool's function: 'Create a new agent thread in a project and send its first message, starting the agent.' This specific verb-resource pair ('create thread') plus the initiating action ('starting the agent') distinguishes it from sibling tools like send_message (which targets existing threads) and list_threads (which only lists). The scope is explicit (project workspace, not UI).

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 implies when to use this tool: when starting a new agent thread in a project with an initial message. It provides contextual details like 'worktree isolation is only available from the T3 UI,' which indicates a limitation compared to the UI. However, it does not explicitly name alternative tools (e.g., send_message for existing threads) or state when not to use it, so it earns a 4 rather than a 5.

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