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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the 'partial' status outcome when the page limit is hit and the extension path via continue_crawl. It omits auth/plan-permission requirements, so not a full 5.

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 short sentences, front-loaded with purpose and then parameter guidance. No filler, every sentence carries information.

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?

With no output schema, the description usefully documents the partial-status return value. It covers the main invocation path but leaves the follow-up retrieval flow (get_crawl_status/get_crawl_results) and permission/plan prerequisites implicit.

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 earns extra by explaining the consequence of omitting max_pages (partial status, extendable via continue_crawl), a semantic detail the schema does not convey even though it documents the default and clamping behavior.

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 (start) and resource (crawl job for a site) and describes the outcome (discovers SEO issues, broken links, page structure). It is immediately distinguishable from siblings like continue_crawl, get_crawl_status, and get_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?

Explains the key decision point for max_pages (omit to reach the plan limit) and routes the agent to continue_crawl for extending a partial crawl. It does not, however, distinguish when to use this vs adjacent tools like create_audit or start_prospect_audit, so guidance is contextual but not exhaustive.

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