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

No annotations exist, so the description carries the full burden. "Runs the same code the tool page runs" is the only behavioral hint and it says nothing about whether an outbound HTTP request is made, whether it is read-only, how redirects or errors are handled, or how rate limiting applies.

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?

It is short and front-loads the resource, which is good, but it is written as telegraphic fragments rather than sentences and "Scope: check" is filler that conveys almost nothing.

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 simple two-parameter tool with no output schema and no annotations, the description should at minimum say what is fetched, how origin is used, and what the result reports. None of that is present, leaving the agent to guess at the tool's output shape.

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 description coverage is 100%, so the baseline is 3. The description adds nothing about the parameters — notably it never explains that "origin" is the value tested against the target's Access-Control-Allow-Origin response header.

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?

"CORS policy" names the resource but supplies no verb, so the agent must infer that this inspects a URL's CORS configuration. "Runs the same code the tool page runs" implies a parity-style check, and the check_* sibling naming supports that reading, but the description never states plainly that it fetches a URL and reports its CORS headers.

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?

"Scope: check" is not usage guidance. There is no statement of when to pick this over siblings like check_csp, check_security, or check_http, and no prerequisites (e.g. that the target must be reachable).

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