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

Annotations already mark it readOnly, idempotent, and non-destructive, and the description adds substantial context beyond that: two calls required, first returns zero by design, ordering is by learned time, deterministic/indexed/cheap, and historical families flow through. Nothing contradicts the annotations.

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 longer than average but every section adds necessary context: polling protocol, alternative, filters, cost/performance, and historical behavior. The key rule is front-loaded. There is some repetition of the learned-time ordering point, but it is used deliberately to emphasize the historical delta behavior.

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 cursor-based polling tool with no output schema, the description covers all critical operational details: how to start, what the first call returns, what the second returns, what filters are available, cost characteristics, and how it differs from search_property_events. An agent has enough to call it correctly without further inference.

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 already high, and the description reinforces filter semantics by naming event type, state, and property/parcel ID. It also clarifies the cursor behavior in plain language ('with no cursor...second, with that cursor'). It adds value beyond the schema even though it doesn't detail every parameter.

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 opens with a specific verb and resource: 'Poll for what is NEW to you' and defines the unique ordering principle ('when DFX learned it rather than by when it happened'). It also distinguishes itself from search_property_events, so an agent can immediately tell what this tool is for without inspecting siblings.

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?

It gives explicit when-to-use guidance, including the exact two-call cursor protocol and the alternative: 'If you want rows now rather than a subscription, call search_property_events instead.' It also explains what must not be used for past-dated facts via within_days, which makes the boundary clear.

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