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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it caps results at 15 with truncation messaging, defines the assessment field values (hold/review/clear), explains how disambiguating inputs alter matching, and discloses false-positive/variant risk, data staleness, and the verify-against-source requirement. No annotation contradiction.

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?

Front-loaded with purpose and return shape, then disambiguators, matchers, assessment, and caveats in a logical order with no filler. It is dense and longish for a single paragraph, but nearly every clause carries information an agent needs for a compliance-adjacent tool.

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 carries the return-value burden and does so: up to 15 scored matches with source links, truncation behavior, and the hold/review/clear assessment. Combined with the disambiguation rules and legal caveats, an agent has everything needed to call and interpret this 13-parameter tool.

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 the baseline is 3, but the description adds real semantics beyond the schema: address flags comprehensively sanctioned regions (with the specific list), owner percentages trigger the OFAC 50 percent rule, phone matches on the last 9 digits, and dob/nationality/country suppress same-name entries whose listed details differ. This meaningfully enriches understanding of what each input does to the result set.

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 specific verb (fuzzy-screen) plus the exact resource and scope: a person or organisation name against OFAC SDN + Consolidated, UN, EU, and UK lists. It also names what comes back (scored matches with source links), which distinguishes it immediately from siblings like company_profile, search_company, or due_diligence_report.

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?

Gives clear context for when each optional input helps (dob/birth_year/nationality/country to set aside same-name matches, owners for the 50 percent rule) and warns that it is informational only, not a compliance determination. It stops short of naming sibling tools or stating when a different tool is the better choice, so it is strong but not fully routing.

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