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

With no annotations provided, the description carries the full burden and does so well: it discloses the `timedOut` reply, that a non-retained cursor yields a whole snapshot instead of missed ops, that nothing is lost between calls via cursor replay, and that mere viewing does not trigger a wake. These are exactly the behavioral traits an agent needs for a blocking/long-poll tool.

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 purpose is front-loaded in the first clause, and nearly every sentence adds actionable detail. It is a dense, somewhat run-on paragraph of many chained clauses, but the information density is warranted rather than padding.

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?

An output schema exists, so return values need not be explained, yet the description still covers the timeout, snapshot fallback, and cursor-replay edge cases an agent must handle. Nothing needed to drive the polling loop correctly is missing.

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 80%, so the baseline is 3, and the description adds real semantics beyond the schema: it clarifies that `afterSequence` should be the delta's `throughSequence` or a snapshot's `lastSequence`, and that `waitSeconds: 0` is a non-blocking poll. It does less for `includeCatalog` and `token`, which the schema already documents.

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 and resource ('Wait for somebody else to change a design and return what they changed') and immediately contrasts it with the alternative behavior ('rather than asking again whether they have'). An agent can distinguish this long-poll from ui_builder_get_design or ui_builder_await_comments without opening a schema.

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?

Gives explicit operational guidance: call again with the same cursor after a timeout, use `waitSeconds: 0` for a non-blocking check, and quote `afterSequence` from the delta's `throughSequence` or a snapshot's `lastSequence`. It also covers the stale-cursor case and the fact that only committed changes wake the caller, so the when/when-not conditions are spelled out rather than inferred.

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