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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds meaningful behavioral depth: it states the screening is not recorded and produces no document, explains that report_url only opens the same search on ofacscreen.com where a PDF can be purchased, and clarifies the cost (free call, paid report). It also discloses the 25-per-day limit and that the score is not a legal finding. This goes beyond the annotations and gives the agent a complete understanding of side effects and limitations.

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?

The description is longer than many but every sentence adds value: it lists the eight lists, mentions fuzzy matching, describes the return format, gives the rate limit, explains the score's meaning, and clarifies the paid PDF option. It is front-loaded with the core purpose and then provides necessary caveats. There is no fluff or repetition; each clause serves a purpose. A slightly tighter phrasing could reduce length, but it remains highly efficient.

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?

Given the tool's simplicity (one parameter), the existing annotations, and the presence of an output schema (which presumably details the returned fields), the description covers all critical contextual aspects: the exact lists, the fuzzy-matching behavior, the free tier and rate limit, the non-recorded nature, the score interpretation, and the report purchase flow. It leaves no ambiguity about what happens when the tool is called, making it fully self-sufficient for an agent to decide when and how to invoke it.

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?

The schema already describes the 'name' parameter thoroughly: 'Full name of the person or entity to screen, e.g. "Vladimir Petrov" or "Acme Trading LLC". Up to 300 characters.' The description adds that fuzzy matching is used, which influences how the parameter is interpreted, but this is more about tool behavior than the parameter itself. Since schema coverage is 100% and the description contributes little additional semantic detail beyond the example, the baseline of 3 is appropriate.

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 immediately states the tool's core action: 'Screen a person or company name against 8 sanctions lists.' It then enumerates the exact lists (OFAC SDN, OFAC Non-SDN, etc.), making it unmistakable what resource is being queried. It also describes fuzzy matching and the output (number of potential matches and top ten scoring hits), fully distinguishing it from any hypothetical alternative. Even without sibling tools, the purpose is precise and unambiguous.

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 provides clear practical usage context: it is free, requires no account, has a rate limit (25 per day), and explicitly warns that the score represents name similarity, not a definitive match. It also explains how to obtain a timestamped PDF via report_url. While it doesn't mention alternative tools or when-not-to-use, the lack of sibling tools makes this less critical. The guidance is actionable and prevents misinterpretation of results.

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