AML / PEP Screening

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

Annotations only indicate readOnlyHint=false, destructiveHint=false, etc., but the description adds critical operational context: PII-sensitive, requires signed DPA, legitimate purpose per call, audit-logged for 60 months, rate-limited to 50 calls/30 min, and returns structured hits with category/sources/match-ratio. This goes far beyond the basic safety flags.

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 average but every sentence contributes a distinct fact: scope restriction, alternative tools, compliance prerequisites, audit/rate limits, and output expectations. It is front-loaded with the core purpose and reads efficiently without redundancy.

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 PII-sensitive compliance tool with 5 parameters and no nested objects, the description fully covers usage boundaries, workflow alternatives, legal prerequisites, rate limits, and a summary of return values. The output schema handles return structure details, so the description is sufficiently complete.

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 only 40%, so the description must compensate. It adds semantic value by explaining `name` must be a single person, `purpose` is free-text compliance justification, and `min_match_ratio` defaults to 0.85. However, it does not clarify `kategori` or `birth_year` beyond schema defaults, leaving some burden unmet.

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 begins with a specific verb and resource: 'Screen ONE natural PERSON's full name against sanctions (OFAC, EU, UN) and PEP lists.' It clearly scopes the tool to natural persons and explicitly distinguishes it from sibling company-focused AML tools such as firmaradar_get_aml_score.

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 explicit when-to-use and when-not-to-use guidance: do NOT pass company names or orgnr, and for company-level risk use firmaradar_get_aml_score. It also prescribes a workflow for company owner/officer screening by first resolving people via get_company_roles/get_company_ownership, then screening each person.

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