snapshot_task_events

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

Despite no annotations, the description clearly states the tool 'only observes task state; it never launches an agent or performs an external action,' which directly addresses potential concerns about side effects. However, it does not mention if previous checkpoints are overwritten or if there are any performance impacts.

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?

Two concise sentences front-load the key purpose and safety guarantee. No redundant words or irrelevant details.

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?

The description covers purpose and behavioral guarantees but does not mention what the tool returns (e.g., success confirmation or checkpoint ID). Given no output schema, this is a notable omission for completeness.

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% coverage with a clear description of 'dueWithinHours' parameter. The tool description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.

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 or replaces the local corpus-diff event checkpoint,' which is a specific action. It contrasts with siblings like 'acknowledge_task_events' and 'poll_task_events' by emphasizing it only observes state and never launches agents or external 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?

No guidance on when to use this tool versus alternatives like 'poll_task_events' or 'list_pending_task_events'. The description includes 'WRITE/LOCAL' but does not explain scenarios where snapshotting is appropriate.

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