start_sessionCreates a fresh sandbox containing the task's starting repository and returns a session_id for run_in_sandbox. Use it to open an independent workspace, then close it with end_session.
Create a fresh sandbox containing the task's starting repository. Returns a session_id for run_in_sandbox. Each session is independent; end it with end_session.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | Task id from list_tasks |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only supply openWorldHint=false, so the description carries most of the burden and does add real behavioral facts: the return value (session_id), the independence of each session, and the requirement to terminate via end_session. It stops short of saying what happens to an unclosed session or whether the sandbox has a time limit.
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?
Two short sentences with zero filler; the core action and return value come first, and the lifecycle notes follow. Nothing could be removed without losing information.
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?
With one required parameter, no output schema, and thin annotations, the description covers what is needed: what is produced, what is returned, and how the session is closed. A single-parameter creation tool needs little more.
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?
The single task_id parameter is fully documented in the schema (100% coverage), and the description only implicitly links it to the starting repository via 'the task's starting repository'. Baseline 3 applies since the schema already does the work.
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 ('Create a fresh sandbox containing the task's starting repository') and immediately ties it to its siblings by naming run_in_sandbox and end_session, so the agent can place it in the workflow without opening any schema.
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 clear lifecycle guidance: the returned session_id feeds run_in_sandbox and the session must be closed with end_session. It does not explicitly state when to create a new session versus reuse an existing one, but the independence statement covers the main decision.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.