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

Annotations already cover read-only and idempotent behavior, so the description adds meaningful context beyond them: one result block per input, input-order preservation, and per-name billing. It does not fully describe the result block structure, but nothing contradicts the annotations.

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 short sentences deliver the core batch capability, output ordering, and billing implication with no filler. The most decision-relevant fact, the 50-name cap, is front-loaded.

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?

The description covers invocation scope, result ordering, and billing, while annotations cover safety. However, with no output schema, 'result block' is under-specified; an agent cannot tell what fields a block contains, and there is no guidance for exceeding 50 names or selecting among closely related screening tools.

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 100%, so the schema already documents names, limit, sources, and threshold. The description reinforces the 50-name maximum and result ordering, but adds little semantic value beyond what the input schema provides.

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 a specific action ('Screen') and resource ('up to 50 names') and makes the batch nature explicit. This clearly differentiates it from the sibling tools sanctions_screen_entity and sanctions_screen_address, which operate on a single entity or address.

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 implies batch use by stating the 50-name cap and per-input result blocks, but it never explicitly says when to choose this over single-screen siblings or what to do for more than 50 names. There is no exclusion guidance or naming of alternatives.

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