start_crawl

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

With no annotations provided, the description carries the behavioral disclosure burden. It reveals that the crawl runs in the background, returns immediately, can block when wait_seconds is set, and that config files are rejected on the free tier. This is substantial and useful context beyond the raw schema.

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 front-loaded with the core behavior, followed by a compact parameter block. Every line provides necessary operational detail, and no content is redundant with the schema. The formatting makes it easy for an agent to scan.

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 six parameters, no annotations, and no output schema, the description is remarkably complete. It covers invocation, return behavior, polling strategy, licensing constraints, and mode trade-offs. An agent has everything needed to call the tool correctly and set expectations.

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 fully document parameters. It does so admirably: url, label, full, everything, config, and wait_seconds each receive meaningful explanations, including defaults, trade-offs, and licensing caveats. This goes far beyond the bare schema titles.

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 states a specific action ('Start a headless Screaming Frog crawl in the background'), names the resource, and distinguishes itself from the sibling crawl_status tool by noting it returns a job_id immediately and should be polled. This is clear and unambiguous.

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 gives clear guidance on parameter usage and points to crawl_status for polling. It also explains when to use full mode for sites over ~500 pages and cautions about config licensing. It does not explicitly list when not to use the tool, but the context is sufficient for an agent to choose correctly.

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