Jithox EU Counterparty Sanctions Preflight

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

Annotations already indicate readOnlyHint and destructiveHint, so the bar is lower. The description adds useful behavioral context: possible result statuses ('found' / 'not_found' / 'unavailable') and that every result carries source, publication date, checksum, and retrieval time. This goes beyond the annotations, though it does not cover auth or rate limits.

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 two sentences, front-loaded with the main action, and every clause adds value: field list, targeted use case, result statuses, provenance, and disclaimers. There is no filler or repetition.

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?

Given the output schema exists and annotations cover safety, the description provides sufficient context: what input to use, what the output includes, and the limitations of the result. A minor gap is that it does not mention behavior when logicalId is missing, but that is likely addressed by the schema and the 'surfaced by a prior screen' hint.

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 100% for the single parameter logicalId, whose description already explains it comes from a prior screen candidate. The tool description repeats this notion but adds no new parameter-level meaning, so the baseline of 3 is appropriate.

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 clearly states the tool returns the full official listing detail for a candidate logicalId, enumerating the fields (names, programme, legal basis, listing date, identifier types, countries). It distinguishes itself from siblings by focusing on retrieval of an official listing for a prior-screened entity, but does not explicitly name alternative tools.

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 states the intended use: retrieving detail 'for a candidate logicalId surfaced by a prior screen', which ties it to the screening workflow. It also provides exclusions: 'Screening evidence only; not a legal/compliance determination, not a clearance.' However, no explicit alternative tools are named for when not to use this one.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful behavioral context: the tool returns 'found'/'unavailable' statuses, and every result carries source, publication date, checksum, and retrieval time. It also adds the caveat 'Reference only, not legal advice', which goes beyond structured annotations.

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 compact and front-loaded with the core action. Each sentence adds value: the enumeration scope, the status values, the legal caveat, and the result provenance. No fluff or 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 zero-parameter, read-only enumeration tool with an output schema, the description fully covers purpose, scope, statuses, and result guarantees. It is contextually complete given the tool's simplicity and the existing annotations/output schema.

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?

The tool has zero parameters, so the empty schema leaves no ambiguity. The description compensates by clarifying what each result includes (regulation/legal basis, since date, subject count, provenance metadata), even though it does not need to explain parameters.

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 uses a specific verb 'Enumerate' and names the resource 'EU sanctions programmes/regimes' with explicit detail (regulation/legal basis, since date, subject count). It distinguishes itself from sibling screening tools by labeling this the 'policy-layer read', clearly identifying its scope.

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 communicates clear context: it is a policy-layer read, reference-only, not legal advice, and operates on the 'snapshot'. It does not explicitly name sibling tools as alternatives or exclusions, but the 'policy-layer read' phrasing implies it is not for entity-level screening.

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?

The description discloses key behaviors beyond the annotations: the receipt is idempotent, Ed25519-signed, and commits to specific elements (HASHED inputs, sources, snapshot checksum, retrieval times, decision states). It also explicitly scopes the attestation as evidence only, not a clearance or legal determination. This adds substantial value beyond the readOnlyHint and destructiveHint annotations.

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 sentences, each earning its place. The description front-loads the core function, then adds crucial limitations in a compact form. No repetitive or vague language.

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?

Given the rich annotations, full schema coverage, and presence of an output schema, the description fully covers the tool's purpose, behavioral constraints, and parameter semantics. It also explains the receipt's evidentiary scope and exclusions, making it complete for an agent to select and invoke correctly.

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?

The schema already provides 100% coverage for both parameters, but the description enriches the 'bundle' parameter by naming additional contents (snapshot checksum, retrieval times) and reinforcing the 'no raw PII' constraint. This goes beyond the schema's brief description, adding meaningful semantic detail.

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 uses a specific verb ('Bundle... into... receipt'), names the resource (screening checks), and clearly distinguishes this tool from siblings by focusing on creating a signed receipt rather than screening or listing. It also clarifies what the receipt is not (a clearance or legal determination), leaving no ambiguity about its purpose.

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 implies when to use the tool: when you need provable evidence of what was screened and when, in the form of a signed receipt. It includes strong exclusions ('not a clearance', 'not a legal/compliance determination') but does not explicitly name an alternative tool or contrast it with siblings, so it falls just short of a 5.

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?

Beyond the read-only and non-destructive annotations, the description discloses deterministic exact-match behavior (no fuzzy matching), possible outputs ('match'/'clear'/'unavailable'), snapshot-scoping, and the non-guarantee of a 'clear'. This is rich behavioral context that helps the agent set expectations.

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?

Two tight sentences deliver the core purpose, matching mode, output values, and key caveats. Every clause earns its place; no filler or 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?

With a rich input schema, output schema, and clear annotations, the description still adds critical context: exact-match behavior, snapshot scope, evidentiary nature, and non-clearance status. It fully equips the agent to understand the tool's limits and role among siblings.

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?

The schema already documents both 'type' and 'identifier' with descriptions and 100% coverage. The description repeats the same identifier type examples from the schema, adding no new parameter-level meaning. Baseline 3 is appropriate when the schema shoulders the semantic load.

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 clearly states it screens an identifier (passport/national id/registration/other) against listed designations' identifiers using deterministic exact matching. This verb+resource definition distinguishes it from siblings like screen_sanctioned_name (which likely handles fuzzy name matching) and the listing/regime tools.

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?

It explicitly notes this is screening evidence only, not a legal/compliance determination or clearance, and that a 'clear' is snapshot-scoped. This sets clear boundaries on use. It stops short of naming alternative tools, but the 'no fuzzy matching' clue implies when to use a different screening path.

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?

Annotations already declare readOnly and non-destructive, but description adds substantial behavioral detail: deterministic match scores, 'unavailable' on missing snapshot, 'never a false clear on outage or fuzzy input', and result metadata (source, publication date, checksum, retrieval time). No contradictions with annotations.

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?

Description is front-loaded with core action and returns, then caveats. Every sentence contributes behavioral or scoping information—no fluff or repetition. Length is appropriate for the tool's complexity.

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?

Given full schema, rich annotations, and output schema, description covers return categories, failure mode, legal scope, and result metadata. It fully equips an agent to select and invoke the tool appropriately.

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 covers all three parameters with descriptions (100% coverage), so description adds little beyond what schema already states. It does not provide format or syntax specifics beyond schema, justifying baseline 3.

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?

Description uses specific verb 'screen' with resource 'counterparty name against a dated snapshot of the official EU Consolidated Financial Sanctions List'. It clearly distinguishes from sibling screen_sanctioned_identifier by specifying name-based screening.

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?

Provides clear context: screening evidence only, not a legal/compliance determination, snapshot-scoped, and behavior on outages. Does not explicitly name alternatives or state when not to use, but the caveats make intended usage unambiguous.

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