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

Beyond the annotations, the description discloses the cost model (per crawled page billed to the customer's DataForSEO account), the async/non-blocking nature, the max page cap, and that only a task_id is returned. These are exactly the operational traits an agent needs before invoking a costly, open-world task.

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 core action and cost warning, then limitations, then retrieval path. Dense but largely waste-free; the workspace note is tacked on at the end rather than integrated, which is a minor structural blemish.

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, yet the description still usefully states that only a task_id comes back. For a 4-parameter async tool this is nearly complete; the missing pieces are the semantics of target (URL vs bare domain) and of respect_sitemap.

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 0%, so the description must carry the load. It explains max_crawl_pages well (required, no default, cost implication, suggested small value) and workspace (optional for single-workspace accounts), but says nothing about respect_sitemap and only implies that target is the domain. Roughly half the parameters are covered.

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 names a specific verb and resource ('Startet einen asynchronen OnPage-Crawl einer Domain') and adds scope (max 1000 pages). It also distinguishes itself from siblings by stating it only returns a task_id and pointing to dfs_onpage_crawl_results for results.

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 context, an explicit limitation (no JS rendering, so JS frontends lose content) and names the alternative (dfs_lighthouse_live) for rendered page checks. It also states the follow-up retrieval tool and the expected delay in minutes.

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