submit_task

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

With no annotations, the description carries the full burden, and it does disclose real behavior: the auto plan chain resolves to a model, then a live agent, then rules, and the sdlc pattern requires the user to approve the spec and confirm before shipping. It stops short of saying whether submission blocks, what is returned, how dedupe behaves, or what budget exhaustion does, which are material for a fan-out/mutation tool.

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?

It is information-dense and the core action leads, but the body degenerates into a semicolon-and-pipe run-on that mixes pattern names, the sdlc workflow, dag field lists, and budget keys in one block. No wasted words, but the structure makes it harder to parse than a short bulleted breakdown would.

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?

For an 11-parameter tool with nested objects and no output schema, the description covers the structurally complex arguments well but omits return behavior, blocking semantics, and several scalar parameters. An agent could invoke it, but not confidently predict the outcome.

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 description coverage is 0%, so the description must compensate for 11 parameters. It does solid work on the complex ones (pattern values, stages, the dag entry shape, budget sub-keys, context_pack as a prefix, agent as a step pin), but leaves n, dedupe, api_key, and project entirely unexplained, so coverage is partial rather than complete.

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 opening sentence gives a specific verb and resource ('Split a task across the agents'), which cleanly separates it from siblings like claim_subtask, start_work, and handoff that consume rather than create work. It never names those siblings, so differentiation is achieved by implication rather than explicit routing.

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 enumerates the pattern choices (auto, plan_execute_verify, cross_review, debate, consensus, parallel, sdlc, dag) and describes what 'auto' falls back through, which is genuine in-tool selection guidance. It never says when to reach for submit_task versus the surrounding lifecycle tools (claim_subtask, start_work, pickup), so usage is implied rather than stated.

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