checkpoint_create

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

With no annotations provided, the description carries the full burden. It discloses that the tool creates a git-tag, captures HEAD, and returns a detailed dict. However, it does not mention potential failure cases (e.g., if the task doesn't exist or if the tag already exists), which would improve transparency. Still, it is generally transparent for a simple create operation.

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 and well-structured: first sentence declares the action, second explains the purpose, then lists parameters succinctly, and ends with return value. Every sentence adds value with no redundancy.

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 output schema is described in the description (though not shown in the input), the description covers inputs, outputs, and purpose. It could be improved by noting whether overwriting an existing step_index is allowed or if there are side effects. However, for a create tool with three parameters, it is largely complete.

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 description coverage is 0%, so the description must explain parameters. It does so effectively: task_id is the task's worktree, step_index is a caller-assigned integer (advises monotonically increasing), description is optional human-readable label. This adds significant meaning beyond the raw schema, especially for step_index which has no enum or default.

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 it creates a git-tag checkpoint at the current worktree HEAD, explaining the action with specific verb ('Create a git-tag checkpoint') and resource ('current worktree HEAD'). It also distinguishes itself from siblings like checkpoint_list and session_rewind by focusing on creation, not listing or rewinding.

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 when to use (snapshotting the worktree for later rewinding) but lacks explicit guidance on when not to use or alternatives. It does not mention other checkpoint-related tools like checkpoint_list for listing or session_rewind for using checkpoints, though the purpose is clear enough for most agents.

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