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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description adds substantial context on top: supported vs unsupported formats, the exact fallback payload (supported: false, overall_risk: unknown), and the crucial caveat that 'no findings does not mean no metadata' for unrecognized formats. It also discloses pricing (0.002 USDC per file), which is behavioral information no annotation or schema carries.

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?

Four tight sentences, front-loaded with purpose and then scope limits and cost; nothing is padded. The 'MCP tool: `scan_metadata`' clause restates the already-known name and is the one piece of low-value text, but the price sentence earns its place.

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?

There is no output schema, so the description has to convey return shape on its own; it does so by naming the risk rating, the supported flag and overall_risk, plus the fallback values. Remaining gaps are minor — the full field set of the findings list and the individual risk scale are not described.

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?

With a single parameter and 100% schema description coverage (the schema already states base64-encoded bytes with a 4 MiB cap), the baseline is a 3. The description adds no further meaning about the input — it never mentions encoding or size limits, so it neither helps nor hurts.

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 opens with a specific verb and resource ('Lists EXIF, XMP and PNG text metadata with a risk rating') and enumerates the inspected formats, so the agent knows exactly what the tool reports on. It does not explicitly name a sibling such as clean_metadata to contrast read-only inspection with removal, so sibling differentiation is left implicit.

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?

The description gives clear scope conditions by listing supported formats and stating that any other format returns supported: false, which effectively tells the agent when the tool will not do useful work. It stops short of routing the agent to an alternative (e.g. a cleaning or compliance sibling) once risk is found.

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