new_task

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

With no annotations provided, the description carries full burden. It discloses key behavioral traits: resetting loop-level self-state but retaining cross-task prototypes and caution. This is fairly transparent, though it could detail more about the nature of these items. Score 4 due to useful disclosure beyond a minimal statement.

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 a single, front-loaded sentence in Chinese that efficiently conveys the core action and behavioral changes. Every word earns its place with no redundancy. Exceptionally concise and well-structured.

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?

The description covers the main action and key behavioral consequences but omits important context: no explanation of the sessionId parameter, no return value description (no output schema), and no mention of prerequisites like an open session. Moderate completeness given the simple tool shape.

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 0% and the description does not mention the sole parameter 'sessionId' at all. With a single required parameter and no description, the agent receives no guidance on what to provide. Baseline is not applicable as there is a parameter; 1 reflects complete lack of semantic contribution.

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 starts a new task with specific side effects (resetting loop state, preserving prototypes and caution). While it distinguishes implicitly from sibling tools like open_session and close_session, it does not explicitly differentiate, so a 4 is appropriate.

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 the tool is used when starting a new task, but provides no explicit guidance on when to use it versus alternatives (e.g., open_session, decide_step) or any prerequisites. Score 3 reflects implied usage without exclusions or comparisons.

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