Audit website SEO

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds critical behavioral context beyond that: it costs $0.004 per page billed to an Apify account, unreachable pages are free, crawling multiplies cost, and maxTotalChargeUsd caps spend. It also mentions it runs an Apify actor with APIFY_TOKEN and synchronous timeouts. This fully discloses the cost and execution side-effects, going well beyond the annotation hints.

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 information-dense but well organized: it opens with the core function, then usage triggers, then cost and execution details. Every sentence adds value. It is longer than a single sentence but justified given the cost model and crawling behavior. It is front-loaded with the primary purpose, so an agent can quickly decide if it is the right tool.

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?

For a tool with 6 parameters, no output schema, and cost implications, the description is remarkably complete. It covers the input (URLs), the optional behaviors (broken links, crawl), the output (0-100 score and issue list), the cost model, and the spending cap. An agent has everything needed to decide whether to call it and how to set parameters responsibly. The lack of an output schema is mitigated by the explicit description of the return format.

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 already documents all six parameters. The description adds valuable semantics: it explains that maxPagesPerSite defaults to 1 and that higher values crawl internal links, each page charged; it explains checkBrokenLinks as 'optional broken-link checking'; and it ties cost to pages. This enriches the schema meaning without redundancy. A small gap is not elaborating on maxLinksToCheckPerPage, but the schema does.

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 verb ('Run'), a precise resource ('on-page SEO audit'), and enumerates the exact checklist (title, meta, headings, canonical, indexability, structured data, Open Graph, images, speed, robots.txt, sitemap, llms.txt, AI-crawler blocking) plus optional broken-link checking and crawling. It also gives explicit triggers ('when asked to audit, review or improve a site's SEO, or to compare pages'), clearly distinguishing it from sibling tools like check_domain_authority or check_website_traffic_rank.

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 explicitly states when to use the tool ('Use it when asked to audit, review or improve a site's SEO, or to compare pages'). It does not explicitly name alternative tools or exclusions, but the purpose is clear enough and the description adds cost guidance (unreachable pages free, crawling multiplier, spending cap) that helps an agent decide whether to invoke it. A slight gap is not naming sibling tools for contrast, but this is minor.

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