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

Adds substantial behavior beyond the annotations: async execution, robots.txt compliance, sitemap following, Markdown page output, relevance ordering when query is set, and a credit model where limit credits are reserved and the remainder refunded. That cost/reservation detail is the kind of operational context annotations do not cover.

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 tight sentences, front-loaded with the core action, then the query/async behavior, then the return-and-cost contract. No filler.

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 7-parameter async job tool with no output schema, the description covers the essentials an agent needs: async nature, the task-id handoff to crawl_result, content format, crawl rules, and the credit/limit economics.

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 baseline is 3. The description does enrich query (relevance-first ordering) and limit (credit reservation/refund economics), but adds nothing about exclude_paths/include_paths or max_tokens beyond their schema text.

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+resource+scope: 'Start an async crawl of one website', with concrete mechanics (links to max_depth hops, sitemaps, robots.txt, Markdown). This distinguishes it from map/extract/webpage siblings that don't recursively follow links.

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 clear operating context: it is async, returns a task id, and explicitly routes the agent to crawl_result to collect results, plus cost semantics for choosing a limit. It does not, however, state when to prefer crawl over map or extract.

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