oc_task_run_checkpoint

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false. The description adds minimal behavioral context beyond stating it writes a summary and returns metadata. It does not explain consequences of calling on a terminal run, whether it can be called multiple times (non-idempotent), or what triggers side effects like redaction or capping of the summary.

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 front-loaded sentence that efficiently conveys the core action and resource. Every word adds value; there is no redundancy or unnecessary elaboration.

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?

Despite moderate parameter count and no output schema, the description omits key context such as the format or fields of the returned metadata, the behavior when called repeatedly, and the meaning of optional parameters. An agent would need to infer or experiment to understand the full contract of this tool.

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 50% and the description does not add meaning for the two optional parameters (current_cursor, evidence). The schema itself provides descriptions for run_id, summary, and the evidence structure, but the description only reinforces the summary parameter. The agent lacks guidance on how to use current_cursor and when to supply evidence, reducing autonomous invocation accuracy.

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 uses a specific verb ('Write') and resource ('checkpoint summary for a non-terminal TaskRun') and clearly indicates the return value ('checkpoint metadata'). It distinguishes this tool from sibling checkpoint-related tools like oc_checkpoint or oc_task_run_complete by specifying the non-terminal state requirement.

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 mentions 'non-terminal TaskRun' which implies when to use it, but it does not explicitly state when not to use it or provide alternatives. For example, it doesn't clarify when oc_checkpoint or oc_task_run_update would be more appropriate, leaving the agent to infer usage context from the name alone.

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