checkpoint

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

No annotations are provided, so the description must fully cover behavioral traits. It fails to disclose that delete and prune are destructive, what side effects exist, or any prerequisites (e.g., permissions, required state). For a CRUD tool, this is a significant gap.

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 very concise, front-loading the core purpose ('Unified checkpoint CRUD') and operation enum. Every word earns its place, though it could benefit from slightly more structure (e.g., grouping operations by type).

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 6 parameters, no output schema, and no annotations, the description is incomplete. It does not explain return values for list/compare, error states, or how operations like prune or compare work in practice. The tool's complexity demands richer context.

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?

Input schema has 100% description coverage for all 6 parameters, so the baseline is 3. The description adds no extra meaning beyond listing the operations; it does not explain parameter interactions or constraints beyond what the schema already provides.

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 'Unified checkpoint CRUD' and enumerates all operations (create, list, restore, delete, prune, compare), making the tool's purpose and resource obvious. It distinguishes from sibling tools which focus on analysis, code, and project actions.

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 lists operations and their default (list), providing some usage hints. However, it lacks explicit guidance on when to use this tool versus sibling checkpoint-related tools (like capture_* or memory_*) and does not specify when not to use each operation.

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