Stealth check

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

Annotations already declare readOnlyHint=true, and the description is consistent with a passive inspection. It adds real context beyond annotations: the check operates on the *current page* rather than a supplied URL, and the response is 'a verdict plus concrete warnings,' which tells the agent what to expect and how to act on it. It stops short of describing verdict values, thresholds for pass/fail, or whether any signals can be spoofed or are unreliable.

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 purpose, then the inspected signals, then the output, then the usage trigger — a sensible order. The signal list is long but each item tells the agent what the verdict covers; the only mild inefficiency is that it reads as an enumeration rather than prose.

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 explaining returns, and it does so at a high level ('verdict plus concrete warnings'). Combined with the enumerated signal categories, an agent knows what to call and roughly what comes back; only the shape of the verdict itself remains unspecified.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no arguments are needed by framing the check as running against the implicitly active page.

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 ('Fingerprint self-check on the current page') and then enumerates the exact signals inspected (webdriver, UA-CH, plugins, canvas/WebGL, timezone/locale, screen, permissions). No sibling tool does anything comparable, so an agent can identify it immediately.

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?

'Run after opening a protected site' gives an explicit trigger condition tied to a preceding step in a workflow. There are no stated exclusions or caveats (e.g., whether it is valid mid-navigation or on about: pages), but there is also no sibling alternative to route away from.

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