aml

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states subject areas and the legal reference; it does not disclose whether the operation is read-only, what the output format is, whether there is any risk of side effects, or if authentication or rate limits apply.

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 very short, front-loaded with the core purpose, and contains no filler. However, it is so terse that it borders on under-specification, missing behavioral and interpretive details, so it earns 4 rather than 5.

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 values, operational behavior, and how 'ongoing monitoring' differs from a one-time check. It does none of this, leaving the agent with incomplete context for a screening 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 description coverage is 100% for the three parameters (lang, name, limit), so the schema already documents parameter semantics. The description does not add extra meaning beyond the schema, but it is not required to, hence the baseline score of 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?

The description clearly identifies the tool as screening for negative news (fraud, money laundering, corruption, sanctions) and references AMLR Art. 55 ongoing monitoring. It is specific about the domain and intent, but it does not explicitly distinguish itself from the similar sibling tool 'aml_news', so there is slight ambiguity.

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 mentions 'ongoing monitoring' as regulatory context but provides no guidance on when to use this tool versus alternatives like aml_news, pep_check, or sanctions_screen. There are no explicit usage conditions, exclusions, or preferred scenarios.

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 full responsibility for behavioral disclosure. It does not mention whether the operation is read-only, possible rate limits, pagination, or output format. The description only restates the tool's purpose without adding behavioral context.

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 a single sentence that front-loads the key information (AMLR/AMLA/AMLD6 regulatory news) and then efficiently lists all topic keywords. There is no fluff or redundant wording.

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 simple news tool with three optional parameters and no output schema, the description provides the essential topic range but omits information about response structure or any additional behavior. It is adequate for basic understanding but has clear gaps.

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 input schema already documents all three parameters with descriptions, achieving 100% coverage. The description only repeats the allowed topic values, which are already in the schema, so it adds no additional semantic value beyond what the schema provides.

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 identifies the tool as providing AMLR/AMLA/AMLD6 regulatory news and enumerates specific topics. This distinguishes it from sibling tools that focus on screening or lookups, such as sanctions_screen or ubo_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?

The description implies this tool is for retrieving regulatory news and lists topics, but it does not explicitly state when to use it versus alternatives or provide exclusions. The context is implied by the tool name and description but not made explicit.

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 must disclose behavioral traits. It reveals the content (specific milestones and limits) but does not state whether the tool is read-only, what the return format is, whether it calculates anything, or if any authentication or side effects exist. The description is more of a content summary than a behavioral contract.

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 extremely concise: two short sentences. It front-loads the main purpose ('AMLR compliance milestones') and then packs key details efficiently. There is zero fluff or repetition, and every word contributes to understanding the tool's domain and content.

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 simple 0-parameter tool with no annotations and no output schema, the description gives a reasonable overview of the content. However, it does not explain what the tool actually returns (e.g., a list, object, plain text) or how the milestones are presented. It is sufficient for a basic understanding but lacks explicit return-value expectations.

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, and the schema is empty with 100% coverage (meaning nothing is undocumented). Per the rubric, a baseline of 4 is appropriate for 0-param tools. The description adds no parameter semantics because there are none, but it does provide context about the data returned, which helps set expectations.

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 identifies the tool as providing 'AMLR compliance milestones' and even gives key examples (1 July 2026, €10k cash limit, crypto Travel Rule €0). However, it lacks an explicit verb like 'lists' or 'returns', so the exact action is implied rather than stated. It is distinguishable from sibling tools, which focus on screening and checks, whereas this one is about regulatory calendar dates.

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?

No guidance is provided about when to use this tool versus alternatives. The description does not mention any prerequisites, use cases, or exclusions. Context from sibling names suggests it is for compliance milestones, but the description itself offers no explicit direction on when to select it.

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 bears the full burden of disclosing behavior, yet it only names data sources (FATF, EU, AMLR). It does not state whether the tool is read-only, what output format to expect, or any side effects. This leaves significant ambiguity for an agent.

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 extremely concise and front-loaded, stating the core scope in one sentence. However, the heavy use of abbreviations like 'AMLR Art. 16+18' may obscure meaning for agents without deep AML domain knowledge, preventing a perfect score.

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?

The tool has no output schema, so the description should explain return values, but it does not. It also omits details like whether the result is a risk score, a list membership, or a textual report. For a tool with no other structured documentation, this is a significant gap.

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 input schema already fully documents the 'country' parameter with examples (Iran, Nigeria, RU), and the tool description adds no additional parameter-level details. Since schema description coverage is 100%, the baseline score 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 identifies the tool as a country risk assessment based on FATF Blacklist, Greylist, EU High-Risk, and AMLR articles, which differentiates it from siblings like sanctions_screen or pep_check. However, it is a noun phrase rather than an explicit verb+resource sentence, so it falls short of a 5.

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 the tool is for country-level risk screening using specific regulatory frameworks, but it lacks any explicit guidance on when to use this tool versus alternatives. No when-not cases or sibling references are provided, so the usage context is only implied.

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 full responsibility for disclosing behavior. It lists what is checked (server status, backend, cache), but it does not mention whether the operation is read-only, any potential side effects, or the format/type of result returned. This is a notable gap for a diagnostic tool, as the agent cannot infer the safety or output characteristics.

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 a single concise sentence that efficiently enumerates the three areas of health checking. No filler or redundant information exists, and the most important information is front-loaded.

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 and no output schema, the description needed to explain what the tool returns or how the results are presented. It only states what is checked, leaving the output structure and possible values unspecified. For a no-parameter tool, the response format is the primary unknown, so the description feels incomplete.

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 and an empty input schema, so there is no parameter information to explain. Per the rubric, a zero-parameter tool receives a baseline of 4, and the description does not need to compensate for missing parameter details since there are none.

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's scope: it checks AMLOracle server status, backend health, and watchlist cache status. While it lacks an explicit verb like 'check' or 'get', the intent is obvious. It effectively distinguishes from sibling tools, which focus on data lookups like adverse media or PEP checks.

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 the tool is for diagnosing system health, but it does not explicitly state when to use it instead of alternatives or any exclusions. There is no mention of prerequisites or situations where it might not be appropriate, leaving the usage context only implicitly derived from the name and description.

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 full responsibility for disclosing behavior. It discloses the scope of checks and the high-level outputs, which is helpful for a read-like aggregation tool, but it does not mention call boundaries, failure modes, or how the separate checks are combined. This is adequate but not rich.

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 core purpose, and each clause adds value: the list of component checks and the return type. No wasted words or redundant restatement of the tool name.

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 absence of an output schema, the description sufficiently indicates the return payload (risk level and AMLR decision). It does not explain the exact response structure or behavior on missing data, but for a bundled aggregation tool this level of completeness is adequate for an agent to invoke it 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 provides 100% coverage with descriptions for all three parameters (name, country, entity_type), so the baseline is 3. The description does not add any parameter-level details beyond what the schema already states, so no bonus is warranted.

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 performs 'Full KYC in one call' and enumerates the included checks (Sanctions, PEP, Adverse Media, Country Risk), making its purpose unmistakable. It also specifies the output (overall risk level and AMLR decision), and the sibling tool names (e.g., sanctions_screen, pep_check) highlight that this is the comprehensive alternative.

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 phrase 'Full KYC in one call' implies use this when a comprehensive KYC screening is needed, and it distinguishes this from the more granular sibling tools. It lacks explicit when-not-to-use guidance or alternatives, but the context is clear enough for an agent to select it over the individual check tools.

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 burden. It only reveals the data source (Wikidata) and regulatory context, without disclosing limitations, return format, or side effects. The absence of an output schema further amplifies the 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?

The description is two short sentences that immediately state the tool's purpose and regulatory relevance. It is front-loaded and contains no unnecessary words.

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?

Without an output schema, the description should explain what the check returns (e.g., whether the person is a PEP). It also lacks any mention of data freshness, limitations, or behavior when no match is found, making it insufficient for an AI agent to fully understand the tool's output.

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 input schema already provides complete descriptions for both parameters, including an example for 'name' and the optionality of 'country'. The description adds no additional meaning beyond the schema, so it does not compensate for any missing information.

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 'PEP (Politically Exposed Person) check via Wikidata', identifying the tool's function with a specific verb and resource. It distinguishes from sibling tools like sanctions_screen and adverse_media by focusing on PEP 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?

The mention of 'AMLR Art. 22 enhanced CDD for PEPs' implies a compliance context, but the description does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. Guidance is implied rather than explicit.

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 must disclose behavioral traits, and it partially does by listing the return fields. It does not mention whether the lookup is read-only, if there are potential multiple matches, or any rate limits/auth needs. For a simple lookup tool, this is adequate but not rich.

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 short sentences, front-loaded with the core purpose and followed by the return details. Every word earns its place.

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 one-parameter read-only lookup tool, the description is sufficient: it communicates what the tool does and what it returns. It could mention that a sanctions hit is a prerequisite, but this is a minor gap given the simple complexity and the absence of an 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 schema provides 100% coverage for the single 'name' parameter with 'Name to look up'. The tool description adds no additional parameter meaning, so the baseline of 3 applies.

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's function: retrieving the full entity record for a sanctions hit, and specifies the return contents (UN XML detail, aliases, nationality, designation). This distinguishes it from sibling tools like sanctions_screen, which implies screening rather than detailed record retrieval.

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 context of use is implied: it is for when you have a sanctions hit and need the full detail. However, the description does not explicitly state when to use this over alternatives like sanctions_screen or pep_check, nor does it mention any exclusions or prerequisites.

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 burden of behavioral disclosure. It adds meaningful context about the watchlists and list sizes, but it does not disclose what happens on a match, how thresholds are applied, whether results return confidence scores, or any side effects/limitations. This is partial transparency, not full.

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 concise sentences. The first sentence packs the core purpose and data sources, and the second adds regulatory context. No wasted words and the most important information is front-loaded.

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?

The tool has three parameters, no output schema, and no annotations. The description fails to explain what a screening result looks like, how threshold and entity_type affect behavior, or what to do with matches. For a screening tool, this leaves an agent with significant ambiguity about the return contract.

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 input schema already has 100% parameter documentation, including descriptions and defaults. The description adds no extra parameter-level information beyond the schema, 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 a specific verb ('Screen') and a resource ('any name') against a defined set of watchlists (EU FSF, OFAC SDN, UN SC, Interpol). It distinguishes itself from sibling tools like sanctions_detail by focusing on the screening action rather than detailed 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?

The description provides clear context by naming the exact watchlists and legal basis (AMLR Art. 35), implying this tool is for sanctions/AML screening. It does not explicitly state when not to use it or name alternatives, but the scope is unambiguous enough for an agent to select it appropriately.

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 must bear the full burden of behavioral disclosure. It mentions inputs and legal reference but does not disclose whether the tool is read-only, what output format it returns (score, category, details), whether it calls external services, or any side effects. This leaves significant behavioral unknowns for a scoring tool.

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 extremely concise, two segments that front-load the core action and key factors. Every word earns its place, including the AMLR article reference that adds regulatory context. No filler or duplication of schema information.

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 a 6-parameter tool with no output schema and no annotations, the description is insufficient. It fails to explain what the tool returns, how to interpret the risk score, or when to prefer this over siblings. The legal citation lends authority but not practical operational context. An agent would lack key information for correct invocation and result use.

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% with each parameter described. The description adds conceptual grouping by mapping 'amount' to amount, 'corridor' to origin/destination_country, and 'sender screening' to sender_name, which provides value beyond the flat schema. This helps the agent understand which parameters are central to risk scoring.

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's purpose: 'AML transaction risk scoring' with specific inputs (amount, corridor, sender screening). This distinguishes it from sibling tools like country_risk or sanctions_screen, which focus on narrower aspects. The verb 'scoring' and resource 'transaction risk' are specific and unambiguous.

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 usage for AML transaction risk assessment by naming key factors and citing AMLR articles. However, it does not explicitly state when to use this tool over alternatives (e.g., sanctions_screen for list screening or country_risk for jurisdiction risk). It provides clear context but lacks exclusionary guidance.

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 provided, the description carries the full burden of behavioral disclosure. It mentions the data source (GLEIF LEI ownership register) but does not describe what the tool returns, how it handles missing inputs, or whether it performs restrictive access. This is minimal transparency beyond the basic function.

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 a single, well-structured sentence that front-loads the core purpose. There is no filler, redundancy, or unnecessary detail, making it highly concise and easy to parse.

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?

The tool has no output schema and no annotations, so the description should compensate by explaining return values and usage context. It does not describe the output format, error behavior, or what the agent should expect after a successful call. Given the availability of sibling tools in a broader KYC/AML context, this brevity leaves significant gaps.

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%, with both parameters (lei and company) having clear descriptions. The tool description itself adds no extra parameter semantics, so the baseline score of 3 applies per the guidelines.

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's function: 'Ultimate Beneficial Owner (UBO) identification via GLEIF LEI ownership register.' It uses a specific verb ('identification') and resource ('GLEIF LEI ownership register'), and distinguishes from sibling tools like pep_check and sanctions_screen by focusing on UBO rather than PEP or sanction status. The AMLR Art. 42 reference adds regulatory context.

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 provides no explicit guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or alternative tools. The AMLR Art. 42 reference implies a regulatory use case, but there is no clear 'use this for X, use that for Y' instruction.

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 provided, the description carries the full burden of disclosing behavior. It mentions reloading from OpenSanctions and refreshing the cache, which gives some insight into side effects. However, it fails to clarify the default behavior (whether checking freshness triggers a reload if stale) or any potential network dependencies or permissions. This is a moderate level of transparency.

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 extremely concise: two sentences that front-load the core function and then provide parameter-specific guidance. Every word earns its place without unnecessary elaboration.

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?

The tool is simple (one optional parameter, no output schema), but the description is ambiguous about whether both 'check' and 'reload' happen in one call or are mutually exclusive modes. It does not explain what happens when force_reload is false (e.g., whether stale data is auto-reloaded) or what the return value indicates. This ambiguity is significant for an agent needing to invoke the tool 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 description provides 100% coverage for the single parameter, so the baseline is 3. The description adds meaning by framing force_reload as the switch between checking freshness and reloading, and uses the phrase 'refresh cache' to clarify its role. This goes slightly beyond the schema's wording.

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's function with a specific verb and resource: 'Check watchlist freshness and reload from OpenSanctions.' This distinguishes it from sibling tools like sanctions_screen or health_check, which focus on screening or system health rather than watchlist cache management.

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 provides some usage guidance by explaining when to use force_reload=true. However, it does not explicitly state when to use this tool versus alternatives or mention any exclusions. The context for when a freshness check is needed is implied but not fully articulated.

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