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

With no annotations, the description carries the full burden and does well: it discloses the paid model ($0.01/call in USDC on Base via x402 in params._meta['x402/payment']), the HTTP endpoint, transliteration of non-Latin names, and that unscreenable input returns 400 rather than a false clear. Only the return content of a 'changes' check is left unspecified.

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?

Dense and front-loaded — lists, matching fidelity, input types, error behavior, and pricing appear in a tight sequence with no filler. The one inefficiency is that the input-type enumeration describes siblings rather than this tool, so the sentences spend space on the wrong thing.

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 should say what a 'changes' result looks like (e.g., newly listed/unlisted matches since the window), and it does not. It is otherwise complete on cost, transport, and error semantics, but the core value proposition of this variant remains unexplained.

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%, so `days` (default 30, max 400), pipe-separated `names` up to 50, and `threshold` are already documented. The description adds no semantics beyond the schema (e.g., no explanation of what the look-back window means for change detection), so baseline 3 applies.

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 states 'sanctions screening' but never explains what makes this tool the 'changes' variant — the look-back re-screening behavior implied by the `days`/`names` params is absent. Worse, it advertises 'Screen a name, a wallet address, a batch, or your own watchlist', which describes the sibling tools (check_sanctions__screen, __address, __batch, __watchlist) rather than this one, leaving the agent unable to distinguish it from four siblings.

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 when-to-use/when-not guidance and no routing to alternatives is given; instead the description lists modalities that belong to siblings, which could actively steer the agent to the wrong tool. The only hint of its unique role (re-screening over a look-back window) comes from the schema, not the description.

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