task_submit

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

With no annotations provided, the description carries full burden and exceeds it. It discloses network-isolation by default, the detailed egress authorization envelope, DB perimeter enforcement, submit-time security scanning that rejects tasks early, and re-verification at execution. It also clarifies that MCP tools cannot mint signing authority, which is critical behavioral context.

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 long but well-structured into distinct security concerns (network, DB, verification, scanning). Each paragraph adds necessary context for safe usage, and the opening sentence front-loads the core purpose. While dense, the complexity of the security model justifies the length.

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 thoroughly covers the security model, return value, and the roles of critical parameters. It lacks explicit details on task formatting or the exact semantics of lane/agent, but these are less critical given the security focus. The absence of an output schema is partially compensated by the mention of task_id for polling.

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 compensates well for the most complex parameters: network_authorization is explained as an operator-signed envelope, allow_db and db_authorization are described in the DB access context, and allow_net/allow_localhost are clarified as requests rather than authority. However, app_id, task, agent, and lane are not explained beyond their schema titles/defaults.

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 'Submit a task to the Kart sandboxed execution queue' with the specific verb 'Submit' and resource 'Kart sandboxed execution queue'. It also notes the return value ('Returns task_id for polling'), which defines its primary function and distinguishes it from status/list siblings.

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?

Usage is implied by the verb 'Submit' and the mention of polling with task_id, but there is no explicit comparison to alternatives like task_status or task_list. The description focuses heavily on security prerequisites rather than guiding when to choose this tool over others.

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