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

Annotations already cover read-only/idempotent/open-world hints, but the description adds billing semantics ('each name counts as one screen for billing purposes') which is meaningful behavioral context not present in annotations. It also notes return ordering.

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, all front-loaded with the key operational facts: batch limit, return shape, and billing impact. No filler.

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?

No output schema, so the description adequately describes return behavior (one result block per input, in order). For a batch screening tool with no output schema and full annotation coverage, this is nearly complete, missing only explicit alternative routing.

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 baseline is 3. The description adds the max names constraint (50) which is already in the schema's maxItems, but reinforces it; no additional syntax or format details beyond the schema.

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?

States a clear verb (Screen) and resource (names), and quantifies the batch limit. Distinguishes itself from single-screen siblings like sanctions_screen_entity by implying batch behavior, though it doesn't explicitly name the alternative.

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 'up to 50 names in a single call' implies when to use the batch version over the single-entity version, but there's no explicit guidance on when to prefer it vs sanctions_screen_entity or sanctions_screen_address.

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