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

Annotations already declare idempotency, open-world reach, and non-destructiveness. The description adds genuinely new behavioral context by disclosing a per-call cost ($0.02 USDC), but omits what the call returns and why readOnlyHint is false for what sounds like a lookup.

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?

A single front-loaded line with the resource, operation, and cost up front; no filler. Appropriate size for the information it does convey.

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 screening tool with no output schema, nothing is said about the result shape (match/no-match, hit counts, list coverage), and the meaning of the optional 'type' parameter is missing. An agent cannot reliably interpret the response or construct a well-formed call beyond the required name.

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 0%, so the description carries the full burden and contributes nothing: it never explains what 'name' should look like (individual vs. organization string) or what valid values 'type' accepts. This leaves both parameters effectively undocumented.

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?

Names a concrete operation (sanctions screening / entity check) against specific sources (OFAC/EU), which is unambiguous and clearly distinct from all siblings. It stops short of an explicit 'not for X' contrast, but no sibling overlaps enough to need one.

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?

No guidance on when to invoke this versus adjacent tools like wallet-risk or threat-intel, no prerequisites, and no indication of what constitutes a screenable entity. The agent must infer context entirely.

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