US OFAC Sanctions Screening MCP

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

No annotations, so the description carries the full burden; it does add real value by disclosing the 200-name cap, the constraining threshold, and that output is audit-ready with list version and timestamp. It omits what a screening result contains (match/no-match semantics), default threshold behavior, and what happens past 200 names.

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?

A single compact sentence that front-loads the PRO gate and the core capability, then the output guarantee. No filler, though the 'PRO.' prefix is cryptic without context.

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 and no annotations, the description should explain return shape and failure modes for a batch screening operation; it only hints at 'list version and timestamp'. What list is screened against and what a result record looks like remain unknown to the agent.

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 only 33% (only access_token documented), so the description must compensate: it explains names as up to 200 entries and threshold as adjustable, which helps. However, it gives no default, range, or meaning for threshold and doesn't clarify that access_token is the PRO-subscriber credential.

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+resource (screen names) plus a concrete scale limit (up to 200) and adjustable threshold, which contrasts with the singular-sounding sibling ofac_check. It never names the alternative for single checks, so sibling differentiation is implied rather than stated.

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 'up to 200 names at once' framing implies this is the bulk path versus the single-record sibling, but no explicit when-to-use/when-not or alternative routing is given. An agent must infer that ofac_check is the fallback for one-off lookups.

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

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

With no annotations, the description carries the full burden. It usefully discloses that matching includes aliases, that results are the best 3 matches, and that each carries a score, but says nothing about what happens on no match, the match threshold, or any rate/auth constraints.

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?

Three short, front-loaded fragments with no filler; the cost signal leads and the scope and return shape follow. The telegraphic style ("Best 3 matches with score") is slightly clipped but nothing is wasted.

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 and no annotations, so the description is the only source of behavior. It covers cost, scope, alias handling and the shape of the return, but omits no-match behavior, score interpretation, and which OFAC lists are covered.

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?

Only one parameter at 0% schema description coverage, so the description must compensate. It adds real value by saying the input is a person/company/vessel name and is single-valued, but gives no format expectations or examples for the `name` string.

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?

Specific verb ("Screen") plus a named resource (OFAC SDN list) and the entity types it accepts (person/company/vessel). The word "one" implicitly separates it from batch_screen, but no sibling is actually named.

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?

"FREE" and "screen one ... name" imply the use case (single-entity screening at no cost), but there is no explicit when-to-use, no exclusion, and neither sibling (batch_screen, program_list) is referenced as an alternative.

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

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

No annotations are provided, so the description carries the full behavioral burden, yet it says nothing about authentication requirements (the access_token parameter implies a subscriber token is mandatory), pagination behavior via limit, result volume, or what shape the response takes. For a lookup endpoint that may return large result sets, the absence of any operational context is a real gap.

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?

It is short and front-loads the resource, but it is written as fragments rather than a complete sentence, and the cryptic "PRO." prefix consumes space without communicating anything to an unfamiliar agent. Conciseness is achieved through omission rather than economy.

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 annotations, no output schema, and three parameters of which two are undocumented, the definition is under-specified for the calling agent. Missing are the auth requirement, the default/limit semantics, and any indication of what an entry contains — all of which the description would need to supply here.

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 only 33%, and the description addresses only the required `program` parameter — but it does so valuably, supplying four real program code formats that the bare `{"type": "string"}` schema does not convey. The `limit` parameter is never explained, and the auth parameter's meaning is left entirely to the schema description.

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 identifies the resource (SDN entries) and the filtering key (sanctions program code), reinforced by concrete code examples like RUSSIA-EO14024 and SDGT. However, the leading fragment "PRO." is an unexplained abbreviation, and no verb is stated — the listing action is only inferable from the tool name. It does not distinguish itself from siblings ofac_check and batch_screen, which an agent could easily confuse with a program lookup.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the sibling tools that perform screening (ofac_check, batch_screen) versus this lookup-by-program. An agent must infer from the name alone that this enumerates entities by list code rather than screening a specific name.

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