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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the tool is known to be safe and idempotent. The description adds valuable behavioral context: it fetches from a datacenter IP, no JavaScript, reads about a dozen URLs once, and stores nothing. This goes beyond annotations by detailing the crawling behavior and network footprint.

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 a single dense paragraph that front-loads the main purpose and lists checks. While long, every clause adds useful detail (crawler types, check categories, output, storage policy). It is structured logically from what it does, to what it returns, to side effects. No fluff, though it could be split into shorter sentences for readability.

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?

The tool is complex with 22 checks and a structured output. The description enumerates the check categories, explains the crawl methodology, clarifies the output format (score and per-check results), and states the side effects (reads ~12 URLs once, nothing stored). Since an output schema exists, return value details are covered there. The description provides a complete mental model for an agent to decide and invoke the tool 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 domain parameter is already documented. The description reinforces its meaning ('Public domain, e.g. example.com (no path)') by explaining the domain is what gets fetched. It adds the nuance that the domain is used as the entry point for the crawl, though the schema already covers the format. The baseline of 3 is exceeded because the description ties the parameter to the tool's core behavior.

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 clearly states the tool's purpose: it fetches a public domain as search engines and AI crawlers do, runs 22 specific checks, and returns a 0-100 score with per-check results. The verb 'Fetch' and resource 'public domain' are specific, and the tool is distinct from siblings like growthr_fix_order (which likely fixes) and growthr_llms_txt (which focuses on llms.txt), making it easy for an agent to identify when to use this scan.

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 implies usage context (scan a site for SEO/AI readability) and lists the checks, but does not explicitly state when to use this tool versus alternatives like growthr_ai_visibility. However, the clear scope and the sibling names provide implicit differentiation. A more explicit 'when not to use' would elevate this.

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