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

With no annotations, the description carries the full disclosure burden and does add real context: no sign-up required, a single home-page load rather than a crawl, and the finding-ID plus fix format of the output. It omits the read-only nature, whether the scan is synchronous or slow, any rate limits, and what happens on failure.

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?

Two tight sentences, front-loaded with the verb and the graded surface, then the return contract. No filler and no restatement of the title.

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 single-parameter grading tool with no annotations and no output schema, the definition is close to sufficient: it discloses coverage, the one-load model, and the shape of the return value. The remaining gaps are failure modes and runtime behavior, which are secondary for a read-only grader.

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?

Only one parameter exists and schema coverage is 100%, so the schema already defines url with an example. The description echoes the same constraint ('public site', home page only) without adding syntax or format guidance beyond it, so this is baseline.

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?

Names a specific verb (grade) and enumerates the exact resources covered: HTTPS, TLS certificate, security headers and cookie flags, plus the return payload (findings PL-027..PL-036 with fixes). It does not explicitly contrast itself with siblings such as get_check or start_check, so an agent must infer that this is the grading entry point.

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?

Usage is implied rather than stated: 'public site' and '(no sign-up)' signal prerequisites, and 'from one load of its home page' signals the scan model. There is no explicit when-to-use versus get_check/start_check/run_check, and no statement about what to do when a site is unreachable or non-public.

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