harvest_commits

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

With no annotations, the description must carry the full burden of behavioral disclosure. It implies a write operation ('copy ... into the store') but doesn't detail side effects, whether it's destructive, requires specific permissions, or how the store is updated (overwrite vs append). The high-level phrase 'copy' is vague about the actual mechanism and consequences.

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 a single, concise sentence with no fluff. It is front-loaded with the core action and destination. However, it is so short that it borders on under-specification rather than efficiency, but for what it says, it is appropriately sized.

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 has 5 required parameters, no parameter documentation, and no usage guidance, the description is wholly incomplete. Even if an output schema exists, an agent cannot correctly invoke this tool without understanding the parameters and expected context. The description fails to provide the necessary context for safe and correct usage.

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?

The schema has 5 required parameters with 0% description coverage, and the description provides no explanation for any of them. An agent cannot infer what 'effort', 'work_slice', 'path', 'since', and 'until' represent from the description alone. This is a severe gap in usability.

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 states a specific action (copy), a resource (commit metadata), and a source/destination (working tree into store). This is clear enough to convey the core function, though it doesn't explicitly differentiate from sibling tools like 'record_landed_commit' or 'remap_commits'. The verb 'copy' is unambiguous about the operation.

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?

There is no guidance on when to use this tool versus alternatives. The description doesn't mention prerequisites, expected context, or any exclusions. For a tool that interacts with a working tree and store, an agent would benefit from knowing when to choose 'harvest_commits' over similar commit-related tools, but this is entirely absent.

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