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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses that checks are deterministic, fetched from public pages, use no AI model and require no account, that registry lookups are cached 6 hours, that reportUrl is retained 30 days and may be null, that errors return as one plain sentence, and that only domain/path (never query string) is recorded with no IP or page text. This is unusually rich operational and privacy context that annotations alone could not convey.

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?

Purpose is front-loaded in the first clause and every sentence carries non-redundant information about checks, output shape, retention, limits, and privacy. The cost is a dense single block with long compound clauses (the result/field enumeration is especially heavy), which slightly hurts scannability for an agent parsing it quickly.

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 full burden and does so: it names the top-level JSON fields (summary, reportUrl, result), explains the checks/webMcpTools/markdownVersion/agentFiles/mcpRegistry structure including null-vs-empty-list semantics, and covers error format and caching. Nothing an agent needs to call this single-parameter tool correctly appears to be missing.

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% and the single url parameter is well documented in the schema, so the baseline would be 3. The description adds genuine meaning by noting that the checks extend to 'a page and its site' (the domain is inspected too) and that the query string is never part of the recorded/checked identifier, which is not stated in the schema.

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 gives a specific verb (checks) and resource (whether AI agents can use a page and its site) and enumerates the concrete dimensions: labelled forms and buttons, declared WebMCP tools, a Markdown version, agent files and MCP server cards under /.well-known, and MCP Registry listings. That scope is distinctive enough to separate it from most siblings, but overlapping tools such as can_ai_fetch, check_site_files and check_page are never named, so the boundary is inferred rather than stated.

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?

It gives a clear trigger: 'Use it when the person asks whether agents can complete tasks on the site or find its MCP server.' It also lists out-of-scope areas (rankings, keyword volumes, backlinks, how AI answers mention the brand), which helps prevent mis-selection. It stops short of explicitly routing to alternative tools for narrower checks like fetching or site-file inspection.

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