SupplyGraph.AI

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

Annotations include 'openWorldHint: true', but the description adds no behavioral detail. It does not mention potential side effects, external actions, or data mutability. The description neither contradicts nor enriches the annotation; it simply ignores it. With no contribution, the description fails to carry its 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 description is short, but it wastes the available space with a pricing JSON that is not relevant to tool usage. It lacks a clear, structured introduction. The 'Enterprise Change Report' phrase is vague and does not align with the tool's name. Conciseness is not beneficial when content is off-topic.

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 generates a corporate exception report with configurable chapters, the description should explain its purpose, output, and cost implications. The output schema exists but is not described. There is no discussion of the report's content, pagination, or limitations. The description is inadequate even for a simple 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 coverage is 100% and includes descriptions for both 'pid' and 'chapter_name'. The description adds no extra parameter information, but per the rubric, a baseline of 3 is appropriate when schema covers parameters well. It does not harm, but it also does not enhance understanding.

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 merely says 'Enterprise Change Report' and provides pricing JSON. It does not state what the tool does, its scope, or how it differs from sibling tools. Even the title 'Corporate Exception Report' is inconsistent with the description text. No verb+resource is present.

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 gives no context on when to use this tool versus alternatives like 'due_diligence_report' or 'supply_chain_risk_prediction'. It does not mention prerequisites, such as obtaining a pid from 'search_company_candidates', even though that hint exists in the schema. No explicit or implicit usage 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 annotations limited to openWorldHint: true, the description adds a detailed pricing block showing per-chapter credit costs, which is useful behavioral context. However, it does not explicitly describe side effects, report generation behavior, or any prerequisites beyond the schema.

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, but the rest is a massive pricing JSON blob that duplicates the chapter_name enum and adds significant bloat. The description is far larger than necessary for the operational information it conveys.

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 an output schema and full parameter descriptions, the definition is mostly complete for invocation. However, it lacks explicit usage guidance, doesn't clarify the openWorldHint annotation, and the pricing dump is noisy. Overall adequate but with 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?

Schema coverage is 100% with clear descriptions for both pid and chapter_name. The description's pricing block adds cost-per-chapter information not in the schema, helping agents make cost-aware parameter choices, and the schema pid description already explains where to obtain the ID.

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 'Generates comprehensive supplier due diligence reports' with a specific verb and resource, and details what it benchmarks (ownership, legal, financial risk). This distinguishes it from sibling tools like search_company_candidates (search) and corporate_exception_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 provides context ('for compliance and procurement decisions') and the schema references search_company_candidates for pid, but there is no explicit 'use when' statement or comparison to alternative tools. The guidance is implied rather than 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 description mentions that results are for caller-side selection, implying it returns multiple candidates rather than a single definitive match. It also includes pricing information (1 credit per run), which is useful. However, it does not disclose details like rate limits, error behavior, or what happens if no matches are found. The openWorldHint annotation is present but the description adds some context beyond it.

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, with a single clear sentence followed by pricing information. It is front-loaded with the core purpose and includes examples in the schema. No wasted 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?

The tool has a simple interface (one parameter) and an output schema, so the description doesn't need to explain return values. The description covers the purpose, input format, and pricing. It could mention what happens with ambiguous matches or no results, but given the simplicity and output schema, it is largely 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 100% coverage of the single parameter 'text' with a detailed description and examples. The tool description adds no additional parameter semantics beyond what the schema provides, so 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 states the tool searches company candidates by company name with optional country/region filters, and returns matching records with mapped company IDs for caller-side selection. This distinguishes it from siblings like search_region_candidates, which likely searches by region instead.

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 explains the input format (company name with optional country/region) and provides examples, which implies when to use it. However, it does not explicitly state when not to use it or mention alternatives like search_region_candidates, though the sibling list makes the distinction inferable.

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 handling aliases and abbreviations and returning a list, which adds some behavioral context. However, it does not disclose what happens on no match, whether multiple matches are returned, or any edge-case behaviors. The openWorldHint annotation is the only structured signal, and the description does not contradict it but also does not enrich it significantly.

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 that captures the essence, followed by a compact pricing metadata block. No wasted words; efficient and 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 single-parameter search tool with high schema coverage and an output schema, the description provides sufficient context. It covers the tool's function, input scope, and intended consumption. It lacks explicit disambiguation from the sibling search_company_candidates, but the name and description make the purpose clear.

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 fully documents the 'text' parameter, including examples and purpose. The description adds no new parameter-level details beyond restating the function. Since schema coverage is 100%, the baseline of 3 applies; no compensation needed.

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: it 'resolves natural-language country or region names' against a 'geography registry' and returns 'standardized region names'. This is a specific verb-resource combination that distinguishes it from siblings like search_company_candidates and the report/visualization tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for resolving region names but does not explicitly mention when to use this tool over alternatives. It provides a usage context ('for downstream agent and MCP tool consumption') but lacks exclusions or direct comparisons to sibling tools. This is adequate 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 are limited to openWorldHint, so the description carries only a modest behavioral burden. It does not mention whether the tool is read-only, whether results are deterministic, or how the open-world nature should affect repeated runs. The pricing line adds operational context about credits, but not behavior like side effects or data destruction.

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 descriptive sentence is dense and specific, covering the scope and purpose in one well-structured sentence. The pricing line adds concise operational information without padding. There is no unnecessary repetition or generic filler.

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 it has 2 clearly described, an output schema, and a global annotation, the description supplies sufficient context to recommend and invoke the tool for a geographic concentration check. It spends a sentence on the core capability requiring no additional caveat; the only missing element is permit selection context already covered in the usage_guidelines dimension.

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 provides 100% coverage with rich descriptions for both pid and region_name, including examples and provenance mention of the related candidate search tools. The description itself contributes no additional parameter-level meaning, so basелинев 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Analyzes multi-tier supply chains to detect single-country concentration and quantify geographic dependency across regions.' A specific verb 'Analyzes' is paired with a specific resource ('multi-tier supply chains') and a more defined output ('detect single-country concentration, quantify ... dependency'), setting it apart from sibling tools such as supply_chain_risk_prediction and sg_visualization.

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 situational guidance such as when to use this tool instead of a sibling, when not to use it, or how it relates to the other supply-chain analysis tools. All descriptive content is focused on own action and inputs, leaving the agent to infer appropriate use from the tool list.

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 openWorldHint=true, the tool may have external side effects, but the description doesn't disclose what those are. It only mentions pricing (which is useful) but lacks details on persistence, external calls, or irreversible actions. No contradiction, but minimal behavioral disclosure.

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 concise—one sentence plus pricing. It front-loads the core purpose and avoids fluff. However, given the complexity of the tool and its sibling context, a slightly longer description with usage guidance would be more helpful without being verbose.

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 output schema exists and the parameter is fully documented, but the description lacks usage guidance and behavioral context (e.g., when to use this over other supply-chain tools, any prerequisites beyond pid). It's adequate for a simple read-like tool, but the openWorldHint suggests more context could be needed.

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 fully describes the single pid parameter, including its source and an example. The tool description adds no extra meaning beyond what the schema already provides, so the baseline of 3 is appropriate 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's function: generates global multi-tier supply-chain graphs with full dependency visibility. This is specific and distinguishes it from sibling tools like supply_chain_risk_prediction or sg_chokepoint, which focus on analysis or risk rather than visualization.

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 by mentioning the pid input comes from search_company_candidates, but it doesn't explicitly state when to use this tool versus alternatives. There's no guidance on scenarios where visualization is preferred over reports or risk prediction, leaving the agent to infer based on tool names.

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 lacks transparency about operational aspects such as side effects, return value, or whether 'continuously monitors' implies an ongoing process or a single analysis. The only annotation (openWorldHint) does not compensate for this lack of behavioral detail.

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 succinct and to the point, consisting of a single clear sentence. It avoids redundancy with the schema details and is 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?

While the schema is detailed, the description lacks information about the expected output or how to interpret results. It also does not explain the practical context for the different event types or analysis modes, which are crucial for a complete understanding of the tool's usage.

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 itself provides comprehensive descriptions for all nested properties, and the description of the top-level 'event_info' adds meaningful context about multi-tier supply chain propagation analysis. This fully clarifies the purpose of each parameter.

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: continuously monitors global supply chain risk events and evaluates their impact on a target company. This is specific and distinct from sibling tools like due_diligence_report or tariff_calc.

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 does not provide explicit guidance on when to use this tool versus alternatives. It mentions 'continuously monitors' but does not specify under what conditions this tool should be invoked or when other tools might be more appropriate.

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: true, which indicates the tool may perform actions beyond read-only. The description mentions 'transparent, rule-based outcomes' and includes pricing (10 credits per run), which adds some behavior context. But it does not disclose whether it makes external requests, its side effects, or any rate limits. Given the openWorldHint, more transparency is expected.

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 a brief note on transparency and pricing. The pricing part is additional but unnecessary for tool invocation; however, it is concise overall. No fluff, but the pricing might be considered irrelevant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a complex domain (tariffs), output schema exists, and schema covers parameters, the description is adequate but not fully complete. It does not explain the output format, any limitations (e.g., only certain products covered), or prerequisites. The openWorldHint and high complexity suggest more detail on behavior would help.

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 covers 100% of parameters with descriptions, so the schema already explains product_description and country_or_region. The description mentions these inputs but does not add much beyond that, not detailing allowed formats or giving examples. Baseline 3 is appropriate since schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it calculates U.S. customs duties by combining HTS base rates with Chapter 99 measures, which is specific and distinguishes it from siblings like tariff_classification. However, it does not explicitly name the sibling tools or compare with them, but the verb 'calculates' and resource 'U.S. customs duties' are clear.

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 this tool: when a tariff calculation is needed, listing inputs like product description and origin. It does not explicitly state when not to use it or mention alternatives, but the differentiation from tariff_classification is implicit. Sibling names are not referenced.

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

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

Beyond the sparse openWorldHint annotation, the description offers only marketing-level claims like 'correct HTS codes' and 'ensuring customs compliance in real time.' It does not disclose uncertainty/confidence, verification needs, failure modes, or any side effects. Pricing is the only concrete added behavioral/cost detail.

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: two purposeful sentences plus a structured pricing note. There is no filler, and key capabilities and cost are front-loaded. The only slight inefficiency is the promotional tone of 'ensuring customs compliance in real time.'

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 tool with a full output schema, the description covers the basic purpose and input modality. It is incomplete in disambiguating against tariff_calc and in setting expectations about classification caveats or confidence, but the output schema reduces the need to describe return values.

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 single parameter is already clearly described in the schema. The description's 'from text or documents' mildly reinforces that the input is free-form text, but it does not add additional parameter semantics beyond what the schema provides, so it hits 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 uses a specific verb ('classifies') and target resource ('products into HTS codes'), and adds input modality ('from text or documents') plus the automation/compliance purpose. This makes the tool's core role clear and implicitly distinguishes it from sibling tariff_calc, which is about calculation rather than classification.

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 'from text or documents' implies when to use it — for HS/HTS classification from unstructured product descriptions. However, it never explicitly states when not to use it or names alternatives (e.g., tariff_calc for calculating duties), leaving the selection boundary to inference.

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