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

Goes well beyond the annotations: discloses that the report is e-mailed by JustIdea Agency (third-party data flow), the ~10-30s runtime, a 2-per-e-mail-per-day rate limit, and that results arrive without fixes until the full report. The only disclosure missing is whether the scan is billed or how long emailed reports take, so a 4 rather than a 5 against the already-informative openWorldHint/readOnlyHint=false annotations.

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 purpose and return format, then constraints, then the fallback routing. Every sentence carries an operational fact, but the prose is dense and mixes what-it-does, consent, rate limits, and error handling into a single run-on block, slightly hurting scanability.

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 naming the return payload (grade A-F, score, problems list) and the 'running' status that routes to get_scan_result. Consent, rate limits, timing, and the e-mail delivery channel are all covered, leaving nothing essential for a correct call.

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 baseline is 3, but the description adds semantics the schema does not: zgoda is a consent gate the agent must obtain before setting true, and email must be the user's own real address rather than a guess. That materially shapes how url, email, and zgoda get populated.

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 (scan/check) and resource (website AI visibility) and enumerates exactly what is inspected: crawler access via robots.txt/firewalls, JS-free readability, structured data, llms.txt, and citation signals. An agent can distinguish this from scan_analytics, get_page, or search_site without opening any schema.

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?

Explicit when-to-use and how-to-use: tell the user the report goes to e-mail, obtain consent under the named privacy policy, set zgoda only after agreement, never invent an e-mail, and poll get_scan_result with the scan_id if status is 'running'. It even names the concrete alternative and the delay (30-60s) for it.

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