Commit Checkpoint

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

Annotations indicate readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds crucial context: 'canonical mutation', idempotency behavior ('reuse the same idempotencyKey', 'replay returns the first canonical result ID and version'), and human approval requirement. No contradiction with annotations.

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 structured with clear 'Use when', 'Do not use when', 'Requires', 'Effect', 'Human approval', 'Then', 'On failure' sections. It is front-loaded and every sentence adds value, though slightly lengthy for a simple tool.

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?

Given the tool complexity (7 params, nested objects, output schema exists), the description covers approval flow, idempotency, failure modes, prerequisites, and follow-up actions. It is comprehensive without needing to detail return values since output schema is provided.

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?

With 57% schema coverage, the description adds value by explaining idempotencyKey reuse policy and binding approvalEvidence to server draft digest. While some parameters still lack detailed explanation, the description compensates well for the gap.

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 purpose: 'commit the exact reviewed draft after explicit user approval of the checkpoint commit.' It distinguishes itself from siblings like 'checkpoint' and 'discard_checkpoint' by focusing on the commit action after human review.

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 explicitly says 'Do not use when: a narrower tool better matches the intent, the project scope is unresolved, or the user has declined the action.' It also provides guidance on idempotencyKey reuse and human approval requirements, giving clear when-to-use and when-not-to-use context.

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