vigo-mcp

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

The description adds behavioral context beyond the readOnlyHint and openWorldHint annotations: it explains that VIGO will 'plan the execution strategy, gather information from multiple sources (regulations, enforcement, knowledge graph), and synthesize a comprehensive report.' This sets expectations about the tool's autonomous multi-step behavior and information sources. It does not contradict the 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 two sentences long, with the core purpose stated first. It is concise, free of redundant phrasing, and each sentence contributes valuable context (what it does, how it works, and when to use it). No words are 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?

Given the tool's complexity (autonomous multi-step task) and the absence of an output schema, the description provides sufficient context: it explains the execution strategy, information sources, and expected outcome (comprehensive report). It could elaborate on report structure or limitations, but the provided context covers the essential decision factors for an 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 description coverage is 100%, and each parameter (task, context, output_format) has a descriptive schema definition. The tool description itself does not add meaningful parameter-level details beyond what the schema already provides, so the baseline score 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 purpose: 'Execute a complex multi-step regulatory task autonomously.' It uses a specific verb ('execute') and resource ('regulatory task'), and distinguishes itself from sibling tools by positioning itself as a general autonomous executor rather than a specific single-purpose lookup. Examples like due diligence and compliance planning reinforce this distinction.

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 explicit use cases: 'Use for due diligence, compliance planning, license acquisition roadmaps, or any task requiring multiple analysis steps.' This gives clear guidance on when to invoke it. However, it stops short of naming alternatives or explicitly stating when not to use it (e.g., for simple lookups, use sibling 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?

Annotations already declare readOnlyHint=true, and the description adds valuable behavioral context by specifying what the tool returns (compliance items with legal references, SOP guidance, case law, and grey area analysis). This goes beyond the annotation and helps set expectations, though it doesn't disclose any limitations or edge cases.

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 action and resource, and every word adds value. It avoids redundancy and gets straight to the point without unnecessary details.

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 tool has no output schema, the description appropriately explains what the search returns, which is critical for the agent. It covers the main use cases and provides enough context for a straightforward read-only lookup tool, though it could mention ordering or result format for full completeness.

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 100% and each parameter is described. The description enhances the query parameter by mentioning 'MIC function (CF1-CF8)' and providing examples, which adds context beyond the schema. It also aligns the 'category' parameter with 'topic' and 'licence_type' with 'licence type', reinforcing meaning.

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 searches the SFC compliance checklist, specifying the dimensions (topic, licence type, MIC function) and the type of results (legal references, SOP guidance, case law, grey area analysis). This is a specific verb+resource combination that distinguishes it from siblings like query_regulation or search_enforcement.

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 explicitly says 'Use for questions about regulatory obligations, MIC responsibilities, procedural guidance, or compliance requirements,' providing clear context for when to use the tool. However, it does not explicitly mention when not to use it or name alternative tools, so it falls 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?

Annotations already include readOnlyHint: true, so the safety profile is known. The description adds value by detailing what behavioral coverage the assessment includes (FRR capital, RO configuration, MIC roles, etc.), giving the agent a clearer picture of the tool's output focus.

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 verb and resource, and every clause adds useful information (inputs and coverage areas). There is no wasted verbiage.

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 provides a useful summary of the assessment's content areas, which helps set expectations. Parameters are fully documented in the schema, so the description adequately complements the structured data for this moderate-complexity 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%, so the baseline is 3. The description only says 'Input company profile' without adding any new parameter-specific meaning beyond what the schema already 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 uses a specific verb ('Perform a compliance health check') and resource ('licensed corporation'), and enumerates distinct coverage areas (FRR capital, RO configuration, MIC roles, annual obligations, regulatory focus areas). This clearly differentiates it from sibling tools like risk_assessment or compliance_score.

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 tells the user to input a company profile and receive a risk assessment, but does not explicitly state when to choose this tool over alternatives (e.g., compliance_score, risk_assessment) or provide exclusions. Context 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?

Annotations already declare readOnlyHint=true, so the description correctly reflects a read-only calculation with no destructive behavior. It adds useful context beyond annotations by specifying the input source and the exact return fields, though it does not describe any potential error handling, rate limits, or authorization details.

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 includes only essential information about the input and output. No wasted words or redundant details.

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 single-parameter tool with no output schema, the description adequately covers the input source and explicitly lists all return components. However, the exact meaning of 'score percentage' and how the returned fields relate to one another are left somewhat implicit, so it is not fully complete.

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 full coverage for the single parameter, describing company_id as 'Company UUID from OrphicOne Portal.' The description's phrase 'from the Portal system' essentially repeats the schema's information without adding new format, constraints, or value semantics. Therefore, it meets the baseline but does not exceed it.

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 and resource: 'Calculate compliance health score for a company.' It clearly names the output metrics (total items, completed, overdue, score percentage), and this differentiates it from sibling tools like compliance_check or risk_assessment by focusing on an aggregate health score rather than individual checks or assessments.

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 a necessary prerequisite ('Requires company_id from the Portal system'), implying the tool should be used when you have a company identifier and need its compliance health score. It does not explicitly mention when not to use it or name alternatives, so it falls 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?

The readOnlyHint annotation already declares the tool as read-only, so the description doesn't need to restate that. The description adds useful content scope (exam, capital, fit-and-proper, CPD) but does not disclose output format, length, or any limitations, leaving some behavioral ambiguity.

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, front-loaded sentence with no redundant or vague wording. Every element (license type, content areas) adds value and the structure is immediately scannable.

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 read-only tool with two parameters and no output schema, the description adequately covers the key query dimensions and content scope. It does not specify the return format, but given the guide nature and annotations, this is not a critical omission.

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 license_type has a schema description (coverage 50%). The description's list of exam papers, capital, fit-and-proper, and CPD hours directly corresponds to the aspect enum values (exam, capital, fit_and_proper), giving semantic meaning to that parameter beyond the bare enum.

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 provides a comprehensive guide for a specific SFC license type, listing concrete content areas (exam papers, capital requirements, fit-and-proper criteria, CPD hours). This distinguishes it from sibling tools like query_regulation and checklist_lookup by focusing on license-specific guidance.

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 conveys clear usage context: it is intended for retrieving a comprehensive guide for a specific SFC license type. It does not, however, explicitly exclude or compare with alternative tools like sop_guide, but the context is specific enough for basic selection.

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 annotations include readOnlyHint: true, which already discloses the read-only nature. The description adds context about the types of updates returned, which is useful but not deep behavioral detail. It does not mention pagination, sorting criteria, time range for 'latest', or any output format. Since the annotation covers the safety profile, a score of 3 is appropriate; it adds some value but lacks richer 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, front-loaded sentence: 'Get latest SFC regulatory updates' followed by a colon and a list of content types. Every word earns its place, with no redundancy or filler. It is highly concise and well-structured.

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 read-only tool with two optional parameters, the description covers the core purpose and content types. However, it omits the output format (e.g., does it return full documents or summaries?), does not define the recency window for 'latest', and offers no mention of how to narrow results using the category parameter (though the schema covers this). The lack of an output schema raises the need for more description of return values, which is absent. Thus it is adequate but not fully complete.

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 a description for 'count' but not for 'category'. The tool description enumerates the category values ('circulars, enforcement news, VATP developments, consultation papers') which corresponds directly to the 'category' enum, adding semantic meaning beyond the bare enum values. For 'count', the schema already describes 'Number of results, 1-10', so the description doesn't need to repeat it. This partial compensation for the 50% schema coverage justifies a 4.

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 'Get' and clearly identifies the resource as 'latest SFC regulatory updates', followed by a concrete list of content types (circulars, enforcement news, VATP developments, consultation papers). This differentiates it from sibling tools like search_enforcement, which focuses on searching enforcement actions specifically, and query_regulation, which likely retrieves regulatory text.

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 only states what the tool does, with no guidance on when to use it over alternatives. It does not mention that for specific enforcement case searches one might use search_enforcement, nor does it describe any exclusions such as 'for point-in-time queries, use query_regulation'. The intended use case (e.g., monitoring recent changes, staying compliant) is implied but not 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?

Annotations already mark this as read-only, so no safety disclosure is needed. The description adds behavioral context by confirming English and Chinese support and the breadth of the knowledge base, though it omits details like whether answers come from a fixed corpus.

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 sentences, front-loaded with the main action and scope. Every phrase contributes 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?

The description is adequate for a read-only knowledge query tool with a required question parameter and optional filters. It lists relevant domains, but could benefit from a hint about response format or when to use specialized 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?

Schema descriptions cover all three parameters (question, language, license_type), so the description doesn't need to explain them. It adds no parameter-specific semantics beyond listing related topics in the 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 opens with 'Query Hong Kong SFC regulatory knowledge,' a specific verb and resource. It enumerates topic areas like licensing and AML/CFT, but does not explicitly distinguish this from sibling tools such as compliance_check or search_enforcement.

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 explicit guidance on when to choose this tool over siblings. The topic list implies its use for general regulatory questions, but exclusions or alternatives are not stated.

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 readOnlyHint annotation already signals a safe read operation. The description adds that it returns a rating with regulatory basis and recommended actions, which is useful behavioral context. However, it does not disclose other traits like data sources, limitations, or how urgency/license_types affect the result.

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 purpose, and contains no fluff. Every word contributes to understanding the tool's core function and output.

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 description covers the core purpose, output type, and key behavior, while the schema covers parameter semantics, making the tool usable. It could benefit from clarifying how urgency or license_types influence the rating, but those details are already in the schema, so the overall package is complete enough.

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%, so all three parameters (urgency, description, license_types) are already documented in the schema. The description does not add any extra meaning to the parameters beyond what is in the schema, so it rests at the baseline.

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 action ('assess compliance risk') and resource ('planned business activity'), and specifies the output format (Red/Yellow/Green). It somewhat distinguishes from siblings like compliance_check or compliance_score by mentioning the color-coded rating, but it doesn't explicitly name alternatives or edge cases.

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 guidance on when to use this tool versus alternatives like compliance_check or compliance_score. The description implies it is for planned activities, but it does not state exclusions, prerequisites, or compare with sibling 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?

The annotations include readOnlyHint=true, confirming a safe read operation. The description adds context about the types of enforcement actions covered and search fields, but does not discuss limitations, pagination, or result format. Since annotations already cover the safety profile, 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, focused sentences. The first sentence states the core function, the second clarifies search dimensions. No extraneous 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 the simple two-parameter search tool with no output schema, the description adequately explains the purpose and search scope, though it doesn't detail result structure. The read-only annotation and parameter descriptions fill remaining gaps, making it sufficiently complete for its complexity.

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?

Both parameters (query, year) have descriptions in the schema covering 100% of parameters. The description's mention of search dimensions ('company, person, or violation type') largely restates the query parameter description, adding no new semantic detail. Baseline 3 applies due to high schema coverage.

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 'Search SFC enforcement actions' with a specific verb and resource, and enumerates included categories (fines, suspensions, bans, prosecutions) and search dimensions (company, person, violation type). This distinguishes it from sibling tools like query_regulation or compliance_check.

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 provides clear context that this tool is for searching enforcement actions, but it does not explicitly mention when to use it over alternatives or provide exclusions. Given the sibling tools, the context is sufficiently specific to imply usage, but explicit alternative guidance is missing.

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, which the description does not contradict. The description adds useful context that returned steps include responsible person, legal basis, and estimated time, but it does not disclose other behavioral aspects like response size, error conditions, or any rate limits. Given the annotations cover the safety profile, a mid-range score is appropriate.

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 long, front-loaded with the purpose, and includes a concise list of available SOPs. Every word earns its place; there is no redundant or filler 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 read-only tool with no output schema, the description explains the output content (steps with responsible person, legal basis, estimated time) and enumerates valid processes. It does not mention how licence_type might affect the response, but given the schema notes it as 'optional context', this is a minor 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?

Schema coverage is 100% for both parameters, but the description adds value by mapping enum values to human-readable process names and explaining what the returned steps contain (responsible person, legal basis, estimated time). This goes beyond the schema's minimal descriptions, providing practical context for selecting process values.

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 retrieves step-by-step SOP guidance for common compliance processes, listing the available SOPs (KYC onboarding, FRR monthly return, complaint handling, STR filing). This distinguishes it from siblings like compliance_check or risk_assessment by focusing on procedural guidance rather than assessment.

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 it (when you need SOP guidance for the listed processes) but gives no explicit guidance on when not to use it or how it compares to alternatives like checklist_lookup or compliance_check. No exclusions are mentioned, leaving the boundary with sibling tools unclear.

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