vibe_submit

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

No annotations are supplied, so the description carries the burden and it does cover the important traits: isolated worktree execution, immediate return rather than blocking, and concurrency serialization when scopes overlap (omit = whole repo). It does not state cost implications despite mentioning a 'cheaper model', nor what happens on failure, timeout, or cancellation, and never says what value is returned for handing to vibe_wait.

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?

Tight and front-loaded: the purpose leads, the parameter glosses follow, and the workflow hand-off is one short line at the end. The telegraphic 'name: meaning' fragments are efficient but border on cryptic for the skill and scope lines, which cost it a point.

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?

This is an 8-parameter mutating/queueing tool with no annotations, no output schema, and 0% schema coverage, so the description must do nearly all the work. It covers the core mental model and next steps well, but omits the four budget/limit parameters and does not say that submission returns a job identifier — a real gap given that vibe_wait, vibe_result, and vibe_apply presumably need that ID.

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% across 8 parameters, so the description is the only source of parameter meaning — and it only explains four of them (spec, skill, scope, base_job). Useful semantics are added for those (where the skill file lives, scope overlap behavior, building on a prior job), but title, max_price, max_turns, and time_limit get nothing beyond self-describing names, leaving half the surface un-elaborated.

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 first sentence gives a specific verb and resource — 'Queue a coding task for Mistral Vibe ... in an isolated git worktree' — naming the executor and the isolation model. It is clearly separable from siblings because the closing line maps the whole follow-up lifecycle (vibe_wait, vibe_result, vibe_apply) and leaves vibe_submit as the entry point. An agent can pick it out without opening a 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?

Usage context is clear: this is the asynchronous delegation path, and the spec guidance ('complete and self-contained; Vibe sees neither this chat nor project docs') tells the agent how to use it correctly. It also directs follow-up to the specific sibling tools in order. It stops short of stating when NOT to delegate or what to do instead (e.g., doing the edit inline), so it is not a full 5.

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