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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds the scan-scoping constraint and the phishing rationale, but says nothing about behavior when a page declares no Open Graph tags or how results are keyed to a scan.

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?

Three tight sentences, front-loaded with what is returned, followed by why it matters and the parameter's meaning. No sentence is redundant and nothing is buried.

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 an output schema present, return values need no explanation, and annotations cover the safety profile. The only residual gap is edge-case behavior (pages with no OG/Twitter metadata), which is minor for a read-only single-parameter lookup.

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 0%, so the description carries the burden for the single parameter and does so: 'scan_id is the UUID of a ScanMalware scan' supplies both format (UUID) and provenance (a prior scan). It stops short of saying whether the scan must be completed.

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?

The description gives a specific verb and resource (retrieve Open Graph and Twitter card metadata) and even enumerates the returned fields (title, description, image, site name). It is clearly distinguishable from siblings like get_ocr_by_scan or get_favicon, though it never explicitly names a sibling to contrast against.

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?

'Phishing pages often copy a brand's metadata' implies the investigative context in which this tool is valuable, which is useful framing. However, there is no explicit when-to-use vs. when-not guidance and no reference to alternative tools for page-content analysis.

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