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

Beyond the readOnly/openWorld annotations it discloses a great deal: results are cached 15 minutes, the checks are deterministic with no AI model and no account, pages are public and fetched by Agent Ready by WorkPods, errors return as one plain sentence, and the reportUrl persists 30 days. It also states exactly what is recorded (domain and path, never query string, tool, failed checks, app name; never IP or page text), which is the kind of behavior an agent cannot infer from 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?

Purpose and when-to-use are front-loaded, and every block (layers, scope exclusions, return shape, privacy) carries information the agent would otherwise have to guess. It is still one dense run-on paragraph with a mid-sentence pivot into return fields, which makes it harder to scan than it needs to be.

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?

There is no output schema, so the description takes on the full burden and meets it: it documents the return shape (summary, reportUrl, result with url, status, per-layer scores, problems, passed, notApplicable), the error format, cache lifetime and the data recorded. For a two-parameter read-only tool this leaves nothing an agent needs in order to call it 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%, and both parameters are already documented with examples, so the schema carries the semantics. The description adds only an indirect hint that a page may redirect ('url (where the page landed)') and otherwise adds no new meaning about how brandName changes the run. Baseline 3 is appropriate.

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 and resource ('Checks one web page') and then enumerates the exact layers inspected: indexing status, robots, canonical, title, meta description, headings, copy, JSON-LD, links, alt text and AI readiness. The phrase 'one web page' plus the explicit note that rankings, keyword volumes and backlinks are out of scope separates it cleanly from siblings like compare_pages, check_site_files and start_site_crawl.

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 states the triggering situation clearly ('Use it when the person asks how a page does in search or AI answers, or what to fix on it') and draws useful scope boundaries by naming what it does not cover. It never names an alternative tool for the adjacent cases (multi-page comparison, site-level crawl, crawler policy), so routing between siblings is left to inference rather than made explicit.

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