SupplyGraph.AI

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

Annotations only include openWorldHint, which is minimal. The description adds no behavioral information such as side effects, output format, authorization needs, or rate limits. The pricing is not a behavioral disclosure of what invoking the tool does.

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 short but contains a large pricing dictionary that is largely irrelevant to the tool's function. This is clutter, not conciseness. The only useful part is the phrase 'Enterprise Change Report', which is unhelpfully vague.

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?

Even with an output schema present, the description completely fails to explain what the tool does. Agents cannot infer the tool's purpose, when to invoke it, or what a corporate exception report entails. It is severely 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 input schema has 100% coverage with good descriptions for both pid and chapter_name. The description adds no additional parameter semantics, but the schema already carries the burden. Therefore, a 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 is essentially a title and a pricing dictionary. It says 'Enterprise Change Report' but does not describe what the tool does, nor does it distinguish it from sibling reports like due_diligence_report. No clear verb or resource is mentioned.

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 on when to use this tool versus alternatives. The pricing information lists optional chapters but offers no context for choosing this tool over siblings.

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 reveals that the tool uses 'global enterprise data' and includes a detailed pricing structure with credit costs per chapter, which is behaviorally relevant and goes beyond the minimal 'openWorldHint' annotation. However, it does not explain side effects, rate limits, or potential long-running nature, leaving gaps in 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 first sentence is concise and impactful, but the description is dominated by a massive, unstructured pricing dictionary that consumes over 95% of the text. While the pricing data is useful, its raw format makes the description unwieldy and poorly structured for quick scanning. It could be summarized or moved to a separate documentation reference.

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 provides an overview and pricing details but omits usage context such as typical time to completion, whether chapters can be combined, or any disclaimer about data recency. Given the tool's complexity and the presence of an output schema, the description is minimally sufficient but leaves room for more completion.

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 description adds significant meaning to the chapter_name parameter by providing a detailed pricing breakdown per chapter (e.g., 'Patent Holdings' at 12045 credits), which is not present in the schema. The pid parameter is not elaborated in the description, but the schema's mention of 'search_company_candidates' already covers it. Overall, the description enhances parameter understanding beyond the schema.

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 starts with a specific verb and resource: 'Generates comprehensive supplier due diligence reports using global enterprise data, benchmarking ownership, legal, and financial risk for compliance and procurement decisions.' This clearly distinguishes it from sibling tools like search_company_candidates and tariff_calc, which focus on lookups or tariff calculations respectively. The purpose is unambiguous and directly tied to the tool name.

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 on when to use this tool versus alternatives like corporate_exception_report or supply_chain_risk_prediction. There are no explicit instructions, prerequisites, or comparisons to siblings. The intended use case must be inferred solely from the name and first sentence.

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 provide openWorldHint, and the description aligns by mentioning 'possible matching records', but it doesn't disclose other behavioral aspects like error handling, rate limits, or side effects. Since annotations are minimal, the description could have added more, but it's not contradictory.

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 clear sentence with supplementary pricing info, front-loading the core purpose without unnecessary fluff. It is 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?

Given the output schema exists and the tool is simple with one parameter, the description covers the essential information including the return of mapped IDs for selection, making it sufficiently complete. It doesn't explain error handling but that may be covered by the 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 already fully describes the 'text' parameter with format details, so the description adds no additional semantic value beyond what the schema provides. The baseline is 3 given 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 the tool searches for company candidates by name with optional country/region filter and returns matches with mapped IDs, distinguishing it from the sibling tool search_region_candidates which likely searches regions. The purpose is 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 company name lookup but doesn't explicitly state when to use this versus alternatives like search_region_candidates, nor does it provide exclusions or prerequisites. It mentions optional filters but no when-to-use 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?

The description mentions the internal geography registry and that it returns standardized names, but does not disclose details like whether it returns multiple matches, how it handles ambiguous inputs, or any rate limits. The openWorldHint annotation is present, but the description adds some context about the registry and downstream use.

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 concise and front-loaded with the main purpose. The pricing information is included but is not directly relevant to tool selection or invocation, adding slight noise. Overall, it is efficient 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?

Given the tool's simplicity (one parameter, clear purpose) and the presence of an output schema, the description is sufficiently complete. It explains the purpose, the input, and the output context. It could mention potential ambiguity handling, but the output schema likely covers return structure.

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 covers 100% of the parameter, providing examples and explaining the purpose. The description adds context about the internal registry and standardized output, but the parameter semantics are already well-covered by the schema, so the description adds marginal value.

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 resolves natural-language country/region names against an internal geography registry and returns standardized region names. It distinguishes itself from sibling tools like search_company_candidates by focusing on regions rather than companies.

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 resolving region names and mentions downstream consumption, but does not explicitly state when to use this tool versus alternatives or when not to use it. However, the context is clear enough for an agent to infer appropriate usage.

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 no behavioral traits such as read-only status, side effects, rate limits, or prerequisites. The only annotation is 'openWorldHint', which is vague and does not clarify behavior. This is a significant gap for a tool that likely queries data.

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 directly states the tool's purpose without extraneous information. It is well-structured and front-loaded with the key action.

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 adequately explains what the tool does but omits details about the output, return format, or any usage context. Given the moderate complexity of the analysis and the absence of an output schema, the description is somewhat incomplete but not critically lacking.

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 detailed descriptions for both parameters (pid and region_name), including how to obtain them (via specific MCP tools). Since schema coverage is 100%, the baseline is 3; the description adds no additional semantic value to the 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 clearly specifies the tool's function: analyzing multi-tier supply chains for single-country concentration and geographic dependency. It distinguishes itself from sibling tools like risk prediction or tariff calculation by focusing on geographic concentration.

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 use this tool versus alternatives is provided. The description implies a use case for geographic concentration analysis, but it does not state conditions or scenarios that would make it preferable to other 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 openWorldHint, and the description says it 'generates graphs,' implying a read/compute operation rather than side effects. It adds some context (global multi-tier, full visibility) but does not disclose potential limitations, permission needs, or any side effects beyond what the annotation hints. No contradiction found.

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, focused sentence that conveys the core purpose, followed by a separate pricing note. There is no extraneous text, and it is appropriately 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 is simple (one required parameter), the output schema is present, and the description covers the primary function. The annotation openWorldHint is not contradicted, and the description adequately explains what the tool does without needing to describe return values since the output schema exists.

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 the pid parameter, including a description, source hint, and example. The tool description adds no extra parameter-level detail, so it stays at baseline 3 for 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 the tool generates global multi-tier supply-chain graphs with full visibility into dependencies, which is specific and distinct from sibling tools like due_diligence_report or tariff_calc. It names the exact resource (graphs) and 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 provides clear context on what the tool does and includes a prerequisite hint to use search_company_candidates to obtain the pid. However, it does not explicitly state when not to use this tool or compare to alternatives like sg_chokepoint.

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 only annotation is openWorldHint: true, with no readOnly/destructive hints, so the description carries the burden of side-effect disclosure. Its verbs ('monitors', 'evaluates') imply non-mutating analysis, and the included pricing line adds cost transparency (264,590 credits per run), but it does not disclose data-freshness behavior, external calls, or failure modes.

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: the first sentence states purpose, and the second provides essential pricing information. There is no filler or redundant restatement of the title or schema.

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 complex, with event-type-dependent fields, nested objects, roles, and modes, but the description only gives a high-level purpose plus pricing. The schema and output schema compensate by documenting parameters and return structure, yet the description still lacks guidance on choosing event types, analysis modes, or interpreting the risk evaluation in context.

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 is richly documented with 100% coverage, including conditional requirements and formats, so the base score is 3. The prose description adds no additional parameter-level meaning beyond the general purpose; the nested event_info description adds methodological context but not semantic detail for individual fields.

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 states a specific action: continuously monitors global supply chain risk events and evaluates their potential impact on a target company. It clearly identifies the core resource (supply chain risk events) and the analytical outcome (whether/how/to what extent a company is affected), which also distinguishes this tool from siblings like tariff_calc or due_diligence_report.

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 should be used when a supply chain risk event needs impact assessment for a target company, but it does not explicitly state when to use it versus alternatives or provide exclusions. There is no mention of event types or analysis modes, so an agent must infer the trigger scenario from the name and schema.

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 the calculation methodology and claims outcomes are 'transparent, rule-based,' which adds context beyond the available openWorldHint annotation. However, it does not mention limitations, data-source assumptions, or that this is a non-mutating lookup-style operation, leaving the description to carry most of the transparency burden.

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 core description is one front-loaded sentence that clearly states purpose and method. The pricing line is an extra detail that may be operationally useful but is not behavior-focused, 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?

For a two-parameter tool with 100% schema coverage and an output schema, the description provides the essential calculation context and expected output nature. It is missing explicit sibling differentiation and limitation caveats, but the overall package is adequate for a straightforward tariff calculator.

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 describes both parameters with definitions, so the description does not need to restate them. The description adds useful algorithm context by referencing HTS base rates and Chapter 99 measures, but it does not add parameter-specific meaning beyond the schema.

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 a specific action and object: 'Calculates U.S. customs duties by combining HTS base rates with applicable Chapter 99 measures.' This clearly states what the tool does and is distinct from the sibling tariff_classification tool, which is about classification rather than duty calculation.

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 should be used when a U.S. tariff/duty calculation is needed, and the method is stated. However, it does not explicitly say when to prefer this over tariff_classification, nor does it provide any when-not-to-use guidance or exclusions.

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 only include openWorldHint and no readOnlyHint or destructiveHint, so the description must disclose whether this operation is read-only or mutating. The description mentions real-time compliance but gives no details about side effects, required permissions, or processing behavior; the pricing line adds cost but not behavioral 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 first sentence is concise and front-loaded with the core purpose. The pricing line is extra but not verbose; no structural issues, though the pricing detail could be considered tangential.

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 an output schema available, the description provides adequate context for selection and invocation, including source (text/documents) and outcome (HTS classification). It could clarify supported document formats or jurisdiction, but the current level is sufficient for simple 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 coverage is 100% and the product_description parameter is already described as identifying HS/HTS codes. The description's 'from text or documents' adds minor context but does not substantially deepen 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?

Description clearly states the tool classifies products into HTS codes from text or documents, with a specific verb and resource. However, it does not explicitly differentiate from the sibling tool 'tariff_calc', and the phrase 'automating tariff lookup' introduces possible overlap.

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 intended use is implied ('Classifies products into correct HTS codes'), but there is no explicit guidance on when to use this tool versus alternatives like tariff_calc, nor any when-not-to-use conditions.

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