AI Search & SEO Audit: GEO, llms.txt & Schema Checker

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

Goes well beyond the annotations (readOnly/openWorld/non-idempotent/non-destructive) by disclosing that the run executes on the caller's own Apify account, costs $0.004 per audited page, that empty runs are not charged per result, and that spend is hard-capped by run_max_charge_usd. These are exactly the billing and account facts an agent needs before invoking a paid, open-world tool.

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 purpose sentence, then an Input/Output line, then a compact paragraph on actor, price, and spend cap. No filler or marketing padding; the only slight redundancy is re-mentioning the charge cap that the schema already explains.

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 carries the burden of describing returns and does so concretely (SEO/AI scores, blocked crawlers, schema, FAQ, author/date, llms.txt, prioritized fixes, Excel). Combined with the pricing, account, and timeout context, an agent has everything needed to decide and invoke 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 description coverage is 100%, so all seven parameters are already documented with defaults, ranges, and behavior (e.g. crawlInternalLinks, generateLlmsTxt, maxPages cost capping). The description only restates 'Input: URLs' and echoes the run_max_charge_usd cap, adding no format or interaction detail beyond the schema, so the baseline 3 applies.

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: audit web pages for SEO and AI search (ChatGPT, Perplexity, Claude, AI Overviews) readiness. It also names the concrete outputs (scores, blocked crawlers, schema, FAQ, author/date, llms.txt, prioritized fixes, Excel), so an agent can distinguish it from every sibling tool in the list, none of which is an SEO/GEO auditor.

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?

Opens with an explicit 'Use this to...' trigger naming the exact task, which gives clear context for selection. It does not state when NOT to use it or name an alternative, but no sibling tool overlaps in function, so the absence of exclusions is a minor gap rather than a real ambiguity.

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