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

No annotations are supplied, so the description carries the full burden, and it discloses the source scope (nine named news editions), the classification scheme, the return shape (risk_level, risk_score 0-100, category counts, dated articles with URLs), the $0.25 USDC cost, and an explicit caveat that results are not an AML determination. Auth requirements, rate limits, and behavior on no-match results are still unstated.

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 the purpose, then scope, taxonomy, return fields, disclaimer, and cost in a compact sequence. The parenthetical country and category lists are dense but each element carries information an agent needs; little is wasted, though the sentence count could be trimmed.

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?

With no output schema, the description usefully enumerates return fields and adds a cost and limitation caveat, which covers the result side well. The input side remains incomplete: four of five parameters are undocumented, which is a real gap for a tool whose filtering behavior (date window, result cap, alias expansion, country override) materially changes results.

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 0% for five parameters, so the description must compensate and largely does not: only 'name' is illustrated via the Wirecard example. The meanings of 'days', 'limit', 'aliases', and 'countries' (whether the country list is a default or overridable) are left entirely to inference.

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 and resource (adverse media / negative news screening of a person or company) plus the risk categories it classifies into. It is clearly separable from siblings like sanctions_screen or kyb_report because it names its domain (public news editions) and its FATF-style taxonomy.

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 use contexts (KYB, KYC, vendor due diligence) and a boundary statement ('screening aid, not an AML determination') that tells the agent how to weight the output. It does not, however, name alternatives such as sanctions_screen or kyb_report, nor say when a different screening tool should be preferred.

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