argus-screen

Screen a name

screen_name

Screens a person, company, or vessel name against PEP, sanctions, entity, enforcement, and watchlist records, returning risk bands and top matches for review.

Instructions

Screen one name against PEP, sanctions, entity, enforcement and watchlist records via Screen Terminal (POST /v1/screen). Returns result_band (strong, possible, weak or none), the per-type bands (sanctions_band, pep_band, watchlist_band) and the top matches. Route on the per-type bands, not result_band alone. Uses one screen from the key's quota. A match is a lead for review, not a finding.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "screen_name"
  }
}

Input Schema

Name	Required	Description
`dob`	No	Date of birth, YYYY-MM-DD preferred (YYYY-MM and YYYY also accepted). People only.
`full`	No	Return the whole API response instead of a summary
`kind`	No	What the name is: person (default), company or vessel. Not sent to the API: for a company or vessel the date of birth is dropped, and for a vessel the country too.
`name`	Yes	Name of a person, company or vessel, in any script
`country`	No	ISO-3166 alpha-2 country code, e.g. RU

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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 does most of it well: it discloses that each call consumes one screen from the key's quota, describes the return fields (result_band, per-type bands, top matches), and warns that matches are leads rather than findings. It does not cover authentication requirements, error/failure behavior, or whether repeated identical screens are deduplicated against quota.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with the action and resource, then outputs, then routing guidance, then the cost and the interpretation caveat. Every sentence carries distinct information with no repetition of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly explains the return shape (result_band values, per-type bands, top matches) and adds the quota cost and the lead-not-finding caveat, which is enough to call and interpret the tool. The remaining gap is the absence of any statement about failure modes or what happens when the quota is exhausted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents name, dob, country, kind and full, including the note that kind is not sent to the API and drops dob/country for certain kinds. The description adds nothing about parameters, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Screen one name') and enumerates the data sources checked (PEP, sanctions, entity, enforcement, watchlist) plus the underlying endpoint. The word 'one' implicitly separates it from the sibling screen_batch, so an agent can pick correctly without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operational guidance: 'Route on the per-type bands, not result_band alone' and 'A match is a lead for review, not a finding,' which tells the agent how to act on output. It also signals the per-call quota cost. It stops short of explicitly naming screen_batch as the alternative for multiple names, so the exclusion is only implied by 'one name'.

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

Deploy Server