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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false; the description goes well beyond them by disclosing that the call blocks until completion, enumerates what the crawl actually checks, and spells out quota/credit consumption plus the important "a failed crawl is not counted" billing exception. It stops short of saying what happens if the timeout elapses (that the crawl continues running lives only in the schema), so it is not fully self-contained.

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?

Front-loaded with the action and scope, then the routing alternative last — a sensible order. The plan/quota sentences are dense but each carries decision-relevant information; a small amount of space could be saved by consolidating the three pricing sentences.

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 the report contents need not be exhaustively described, yet the description still summarizes the checks, which helps the agent decide to call it at all. With 100% parameter coverage in the schema and explicit credit/quota behavior, an agent has everything needed to invoke this correctly.

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 explains url, max_pages and timeout_seconds, making 3 the baseline. The plan-tier sentences add useful framing for max_pages by defining the per-crawl cap it must fit under (25 on Pro, 100 on Ultra), but they do not explain parameter interaction or defaults beyond that.

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 ("Crawl one site and wait for the result") and immediately scopes the behavior: follows same-site links plus the sitemap and reports a named set of findings. The title's blocking/waiting nature is confirmed in the first clause, and the closing sentence names the asynchronous siblings (start_crawl + get_crawl), so an agent can distinguish this from them 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 an explicit routing rule: use start_crawl + get_crawl "for long waits," which tells the agent when this blocking variant is the wrong choice. Plan-tier quotas (25/100 pages, 20/100 crawls) and the Deep Audit credit fallback give concrete preconditions for whether the call will even be permitted.

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