vibe_checkpoint

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 the key gating trait ('the only gate that authorizes writing code') and the pre-work ordering requirement. It omits critical behavior: whether the call blocks until the user responds, what a checkpoint returns, and what happens on sequential calls.

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?

Dense but front-loaded, leading with the core instruction ('BEFORE doing the work') and then enumerating the kinds compactly. Every clause carries information; no filler. Slightly run-on in the kind definitions, which slightly hurts scanability.

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 a 6-param tool with no annotations and no output schema, the description covers the mode semantics but not the response behavior or the remaining parameters. An agent can invoke it, but doesn't know what to expect back or how consequences/proposedAdditions are used.

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 67%, and the description richly explains the 'kind' enum values well beyond the bare enum. However, it adds nothing for name, proposal, consequences, proposedAdditions, or projectPath, leaving the partially-covered parameters undocumented.

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+resource ('open a checkpoint') and then defines the three kinds (build/design/implement) with what each entails. An agent knows exactly what this tool creates. It does not, however, differentiate itself from the sibling vibe_confirm, which appears to cover overlapping confirmation semantics.

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?

Gives explicit per-kind usage conditions: build asks the user's reasoning first, design presents the agreed design, implement is 'the only gate that authorizes writing code.' This tells the agent when each mode applies. It stops short of naming which sibling tool (e.g. vibe_confirm) to use instead in overlapping situations.

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