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

Annotations only declare read-only, open-world, non-destructive; the description adds genuinely new behavioral facts: raw HTML only with no JavaScript execution, a hard 20-URL cap, no site_id prerequisite, and the exact per-URL checks and cross-URL duplicate detection performed. This goes well beyond what the annotations convey.

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 scope, then dense but information-bearing clauses. It is a long run-on sentence, but nearly every clause (no JS, max 20, no crawl) earns its place.

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?

There is no output schema, so the description carries the full return-value burden — and it does, spelling out the extracted elements, per-URL threshold checks, duplicate detection, and the raw-HTML limitation. An agent has everything needed to call and interpret results.

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 coverage is 100% and the single `urls` parameter is fully documented, including the JSON-array-or-comma-separated format and bare-domain handling. The description only restates the max-20 limit already present in the schema, so it adds no meaning beyond structured data — baseline 3 is appropriate.

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 and resource ('Read the SEARCH SNIPPET head of up to 20 public URLs') and immediately scopes it against crawl-based siblings ('no crawl, no site_id'). The enumeration of the extracted fields (title, meta description, og tags, canonical, robots, H1s) leaves no ambiguity about what the tool returns.

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 concrete when-to-use scenarios: competitive snippet teardown ('how do Rox / Klue / Valley write their titles') and post-fix verification of what a crawler now sees. The 'ANY site, competitors included, no crawl, no site_id' clause implicitly routes agents away from start_crawl/get_crawl_results for quick external snippet inspection.

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