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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real value on top: the exact threat classes scanned and the fact that the semantic detection pass is Pro-tier gated. It stops short of saying what a positive finding looks like or how the caller should react.

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 sentences with no filler, front-loading the purpose and threat model before the input guidance. The Pro parenthetical is compact, though the second sentence is a dense run-on of detection categories.

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?

No output schema exists, so the description carries some burden for return semantics, yet it never indicates what the scan produces (a findings report, a verdict, flagged spans) or what the caller should do on a hit. For a pre-flight security gate with two inputs and no documented output, that is a meaningful omission.

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 the two property descriptions already explain url vs content, so the baseline is 3. The description adds only the either/or framing ("Pass either a URL to fetch, or raw text you already have"), which the schema's "if not fetching a URL" clause already conveys.

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 (check/scan) plus resource (document or web page) and enumerates what it detects: invisible Unicode, obfuscated payloads, and a semantic prompt-injection pass. It is clearly distinguishable from scan_extension and scan_mcp_server by targeting arbitrary page/document content, though it never names those siblings explicitly.

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?

Gives a timing cue ("before an agent reads, summarizes, or acts on it") that implies a pre-ingestion gate, which is useful context. However there is no explicit when-not guidance and no routing between this tool and check_output, so the agent must infer which of the two scanning tools applies to its case.

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