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

Beyond annotations, the description discloses that the tool runs in the background, returns a job id immediately, and can take minutes while consuming significant resources. This is valuable behavioral context that annotations alone do not provide and directly affects how the agent should handle the call and set parameters.

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 three sentences with no filler, front-loads the core action, and places the important async/resource behavior immediately after. Every sentence adds operational value, and the parameter warning is integrated naturally rather than buried.

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?

Given the output schema exists and annotations are present, the description covers the essential async contract, result retrieval path, and resource warning. The main gap is the undocumented path-filter parameters, but the tool is still callable with just the required url and safe defaults, so the description is nearly complete.

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 compensate for missing parameter documentation. It only explains limit ('set limit conservatively') and implies url via 'crawling a website', but says nothing about maxDepth, includePaths, or excludePaths, leaving their meaning and usage to inference from their names and defaults.

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 lead sentence 'Start crawling a website' names a specific verb and resource, and the background-job framing distinguishes it from sibling tools like crawlStatus and crawlPages. The description makes clear this tool initiates a crawl rather than inspecting or reading crawl 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?

The description explicitly tells the agent to use crawlStatus for progress and crawlPages for results, giving concrete follow-up routes. It also warns that crawls take minutes and consume significant resources, advising a conservative limit, which helps the agent decide whether this heavyweight tool is appropriate.

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