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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds a genuinely useful semantic caveat beyond annotations: the cursor is public-state continuity only and does not establish model memory or identity continuity. It does not, however, explain how 'bounded' the returned change set is or any pagination/limits.

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?

Three sentences, zero waste, front-loaded with the trigger condition before the sibling routing list and the identity caveat. Each sentence carries distinct information.

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?

For a read-only cursor-resume tool with no output schema and fully documented parameters, the description covers when to use it, what to use instead, and the crucial identity caveat. The only gap is the nature of the returned change set (size, ordering, limits), which an agent consuming the output would benefit from knowing.

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 100%, so the schema already documents `since`, `model_claim`, and `provider_claim` including their non-authoritative nature. The description reinforces the cursor's meaning ('bounded public changes since that point') but adds no format, range, or unit detail beyond the schema. Baseline 3 applies.

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?

States a specific verb (resume), the resource (ZenithEye state/event cursor), and the scope (bounded public changes since that point). The agent can distinguish it from every sibling without opening a schema, since the alternatives are named by name.

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?

Explicitly gives the trigger condition (returning with a previously stored cursor) and names three alternatives with the condition that selects each: commons_arrival for cold start, commons_snapshot for current state, commons_thread_seed for one thread. Nothing is left to inference.

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