checkpoint

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

Annotations provide minimal safety hints (e.g., readOnlyHint false, destructiveHint false), so description carries the burden. The description lists destructive-ish actions like delete_checkpoint and restore/rollback without explaining side effects, reversibility, or preconditions. It does not add behavioral context beyond the schema's action-specific notes (e.g., transaction behavior) and leaves consequences unclear.

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 concise at two sentences. The first sentence captures the core purpose efficiently; the second sentence lists actions, which is somewhat redundant with the schema but provides a useful at-a-glance summary. No fluff or unnecessary detail.

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 tool has 5 parameters, no output schema, and sparse annotations. The description only gives an action list and general purpose, lacking guidance on which parameters are needed for specific actions, return value expectations, or preconditions. This is insufficient for an agent to fully understand how to use the tool correctly across all eight actions.

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 100% with all four parameters described, including the action enum with notes on transaction behavior. The description adds no extra parameter-level detail—it only restates action names. Baseline 3 applies because the schema already documents parameters well.

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 the tool is a 'Checkpoint and transaction system' with specific verbs: 'Create semantic snapshots', 'diff between checkpoints', and 'rollback changes'. It also lists all eight actions, making it distinct from sibling tools like source_control or manage_*.

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 implies usage for snapshotting, diffing, and rollback via the action list, but it does not explicitly state when to use this tool versus alternatives (e.g., source_control) or mention exclusions/prerequisites. No direct 'when to use' guidance is provided beyond the listed actions.

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