check_incremental

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

Annotations already supply the safety profile (readOnly, idempotent, non-destructive, open world). The description adds genuine behavioral context by naming the checkpoint identity ('folder + UIDVALIDITY + UID'), which is not in any structured field. However, it says nothing about what 'replay' yields, how limit affects the batch, or how this interacts with acknowledge_checkpoint; the 'create' verb also sits in mild tension with readOnlyHint.

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 terse sentences, operation stated first, identity scope second. No padding or redundancy; the only knock is that the compression makes the content opaque rather than efficient.

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?

With no output schema and no schema parameter descriptions, the description needs to do more for a stateful incremental-sync tool. It omits return content, pagination behavior via limit, and the relationship to acknowledge_checkpoint, leaving the agent unable to call it correctly beyond guessing.

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 carry the load. It implicitly scopes the operation to a folder via the identity string, but never explains folder's role or what limit (1-100, default 50) controls. Only one of two parameters gets any illumination.

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 names a verb+object ('Replay unacknowledged UID batch or create next batch'), but 'batch' and 'replay' are jargon that never resolve into what the tool actually returns or operates on. It gestures at an incremental mail-sync role distinct from search_mail/read_mail, but the agent cannot confidently map it to a task from this text alone.

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 when-to-use or when-not-to-use guidance, and no mention of the sibling acknowledge_checkpoint, which is clearly the paired tool (acknowledged vs unacknowledged batches). The agent must infer the entire workflow context.

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