start_sandboxed_agent

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

Goes beyond the annotations by disclosing sandbox boundaries (path allowlist), environment isolation (no inherited broker/owner env), runtime quotas, and fail-closed authorization behavior. This gives the agent important operational expectations that the annotations alone do not convey.

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?

One dense, focused sentence with no filler. The core action is front-loaded, followed by the most relevant constraints and authorization requirement. Every clause earns its place.

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?

Covers the essential runtime context: sandbox scope, environment isolation, quotas, authentication requirement, and failure mode. The main gap is the absence of output/return-value guidance, especially since there is no output schema and session results may need to be retrieved via a sibling 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?

The input schema already describes the required 'task' parameter, and 'max_runtime_sec' is reasonably inferable from its name and default. The tool description adds no parameter-level detail, and 'max_runtime_sec' lacks explicit semantics such as what happens when the quota is exceeded.

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 action ('Start'), a precise resource ('AlgoClaw MCP-only agent session'), and a clear scope ('app-owned sandbox'). The sandbox qualifiers distinguish it from generic launch/execute/backtest tools in the sibling list.

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 gives useful context about the sandbox environment and the required agent:sandbox scope, making the intended use reasonably clear. However, it never explicitly states when to prefer this tool over alternatives such as submit_long_running_task or execute_intent, nor does it name exclusions.

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