vibe_start

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

With no annotations, the description carries the full disclosure burden. It does add real value — it creates a .vibe-wise/ directory and drives onboarding one question at a time, which tells the agent this is interactive and stateful. It omits side effects on repeat calls, what happens if onboarding is already complete, and any idempotency or error behavior, which is a notable gap for a no-annotation 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?

A single dense sentence with the core action front-loaded and the behavioral detail in a parenthetical. Every clause carries information; no filler or repetition.

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 what and the when reasonably well, but for a stateful, no-annotation tool with an incomplete schema it leaves out projectPath semantics, repeat-call behavior, and how it relates to vibe_status/vibe_pause. Adequate but with clear gaps.

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 only 50%: 'action' is documented in the schema, but 'projectPath' has no description anywhere. The description never mentions projectPath or explains how the path affects activation, so it fails to compensate for the uncovered parameter.

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 ('activate learning-first mode') and clarifies the scope with concrete behaviors (creates .vibe-wise/, one-question-at-a-time onboarding, resuming a paused state). It does not, however, distinguish itself from any of the nine siblings (e.g., vibe_status, vibe_pause, vibe_confirm), leaving an agent to infer the boundaries.

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?

'Call before the first build task' gives a clear triggering context for the tool. There are no exclusions or alternative-routing statements, so an agent that is mid-onboarding or already active gets no explicit guidance about whether to call vibe_status instead.

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