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

Annotations declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, so the description must add the operational context they omit. Instead it says nothing about what a scan does (active probing? crawling?), whether it hits external hosts, how long it takes, or what the caller must supply to start one.

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 a single short sentence, so there is no padding in length, but "for MCP server" earns nothing and the sentence is under-specified rather than concise. Nothing is front-loaded beyond the bare product label.

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?

A network-facing, non-read-only scanning tool with a free-form open schema and no output schema requires the description to carry the weight. The description omits the target input format, scan scope, and expected result, leaving the agent unable to invoke 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?

The schema has zero declared parameters but sets additionalProperties=true, so the agent must infer from the description what keys to send — presumably a target URL — and the description provides no such hint. With no schema fields to leverage, the description fails to compensate even though an empty param list normally earns a higher 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?

"Web application security scanning module" largely restates the name and title (scanner / Scan Web App Security) rather than stating a concrete verb and resource. The trailing "for MCP server" is pure filler, and nothing distinguishes this scan from web-audit siblings such as lighthouse or linkchecker.

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?

There is no when-to-use guidance, no preconditions, and no mention of alternatives or exclusions. An agent cannot tell what kind of target this applies to or when to prefer lighthouse or linkchecker instead.

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