website_check

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

Adds substantial context beyond the annotations: per-call cost (four probes per payment), no free sample, sandbox simulation without network access, IP/path disclosure to the target, and a warning that target content is untrusted. These are exactly the operational facts an agent needs before spending credits.

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 operation and probe budget, then returns, then safety notes — a sensible ordering. It is slightly redundant, restating sandbox behavior twice ("Sandbox mode returns simulated checks" and "SANDBOX (development): returns dummy data"), which costs a point.

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 compensates by listing the return keys (url, simulated, requests_planned, page, sitemap, links, broken_links_count, coverage). Combined with cost, sandbox, and safety disclosures, an agent has everything needed to call it correctly.

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%, so the schema baseline already documents both parameters; the description nonetheless adds meaning by explaining what happens to link_urls (HEAD probes) versus url (TLS/status check) and reinforcing the same-origin and exactly-two constraints.

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 the specific operations: HTTPS/TLS and status check on one page, GET /sitemap.xml, and HEAD on exactly two same-origin links, quantified as four probes. It also explicitly scopes out redirect following and full-site crawling, which separates it from crawl/audit siblings like page_audit and website_content.

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 clear usage conditions: one public non-confidential HTTPS page plus exactly two same-origin links, no redirect following, no crawl, and sandbox mode for development. It does not name a sibling alternative for when a full crawl is actually needed, leaving that inference to the agent.

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