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

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds that results are grouped by keyword but does not disclose additional behavioral traits like rate limits or error handling. With annotations covering safety, the description offers moderate added 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 concise with a front-loaded purpose, structured Args/Returns sections, and a practical example. Every sentence adds value, and the length is appropriate for a tool with two parameters.

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 (2 parameters, no output schema), the description fully covers purpose, parameter semantics, return structure, and usage example. No gaps are apparent for effective invocation.

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 descriptions for both parameters. The description adds value by providing an example ('keywords=["GDP", "CPI", "出生率"]') and explaining the return format ('按关键词分组的搜索结果'), which goes beyond the schema's basic descriptions.

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 explicitly states it performs batch search for multiple keywords simultaneously, improving efficiency. The title 'Batch Search CNBS Data' and the description '批量搜索多个关键词的统计数据' clearly specify the verb (batch search) and resource (CNBS data). It distinguishes from sibling tools like 'cnbs_search' which likely handles single keywords.

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 indicates usage when multiple keywords need to be queried at once ('一次性查询多个指标，提高效率'), but does not explicitly mention when not to use or name alternatives. However, the context implies it replaces multiple single searches.

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 indicate readOnly, non-destructive, idempotent, openWorld. The description adds that it returns a comparison table (结果表格), but no additional behavioral details like authentication or data source limitations.

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 well-structured with Args, Returns, and Examples sections. It is concise (3 lines of Args, 2 examples) with no redundant 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?

No output schema, so description must cover return values—it mentions '对比结果表格' (comparison result table), which is adequate but lacks details on table structure. Given the tool's complexity and good annotations, this is mostly sufficient.

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%, so baseline 3. The description adds value by providing example parameter combinations and clarifying the relationship between compareType and other parameters (regions for region, years for time).

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 compares CNBS data across regions or time, with specific verbs '对比' and 'compare'. This distinguishes it from sibling tools like cnbs_search which retrieve data without comparison.

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?

Examples show when to use region vs time comparison, but no explicit guidance on when not to use this tool or to prefer siblings. The context is clear for intended use cases.

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, destructiveHint=false, idempotentHint=true. Description adds that it returns 10 indicators with metadata (name, value, unit, time). No contradictions. Could mention output format or limitations, but adequate.

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 paragraphs, front-loaded with purpose. Example provided. Every sentence adds value; no waste.

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?

Tool has zero parameters and no output schema; description fully explains what it returns (10 indicators with metadata). No missing context for a simple aggregated fetch 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?

No parameters exist; schema coverage is 100% (empty). Baseline for 0 params is 4. Description does not need to add param info, and it correctly omits any reference.

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 current values of core macro indicators (GDP, CPI, etc.) in one call, listing all 10 indicators. It distinguishes itself from sibling tools like cnbs_search by aggregating common indicators, avoiding multiple calls.

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?

Explicitly says '适合需要快速了解中国经济全貌的场景，避免多次单独调用 cnbs_search' (suitable for quickly understanding China's economic overview, avoiding repeated calls to cnbs_search). Provides clear when-to-use and alternative.

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 provide readOnlyHint, idempotentHint, and openWorldHint. The description adds behavioral context: it supports extended data sources and discloses the FRED authentication caveat, which is beyond what annotations provide.

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 well-structured with Args, Returns, a warning note, and examples. Every sentence adds value, and the overall length is appropriate for the tool's complexity.

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

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

Without an output schema, the description states '数据源返回的数据' (data returned by the source), which is vague but acceptable for a generic fetch tool. Examples cover major sources, but error handling or pagination is not discussed.

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?

Examples show concrete usage for each source (e.g., source='cnbs' with keyword, source='census' with type and year), adding significant meaning beyond the minimal schema descriptions. Schema coverage is 100% but the description compensates richly.

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 '从特定数据源获取数据' (fetch data from a specific data source) and lists supported sources like cnbs, census, international, department. It distinguishes from siblings (e.g., cnbs_search, ext_fred) by focusing on fetching raw data from a source.

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 warns about FRED authentication limitations and suggests using ext_fred for HTTP mode. It provides examples for multiple sources, but does not explicitly state when to use this tool versus dedicated ext_ tools for other sources.

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 indicate read-only and idempotent behavior; the description adds valuable context about recursion and time consumption, which goes beyond 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 very concise with a clear front-loaded purpose, no unnecessary words, and a structured Args section.

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 tool with one parameter, good annotations, and no output schema, the description fully explains purpose, behavior, and return value.

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 the description repeats the exact same parameter info, adding no new 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 clearly states it recursively fetches leaf nodes under a classification code, which is specific and distinct from sibling tools that fetch nodes, series, or metrics.

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 warns that the operation is time-consuming and not recommended for frequent use, but does not provide explicit guidance on when to use this tool vs alternatives like cnbs_fetch_nodes.

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, destructiveHint=false, idempotentHint, and openWorldHint. The description adds that results are grouped by setId when multiple setIds are provided, which is a behavioral detail beyond annotations. No contradictions.

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 an Args and Returns section, front-loading key information. No unnecessary sentences.

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 no output schema, the description explains the return structure (grouped by setId for multiple inputs). It covers both parameters adequately, though it does not address error scenarios.

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%, but the description adds value by specifying that setIds come from specific sources and that name filtering is only for single setId. This aids correct invocation beyond the schema descriptions.

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 fetches all available metrics for given dataset IDs, specifying it can handle multiple setIds. It distinguishes itself from sibling tools like cnbs_search and cnbs_fetch_nodes by focusing on metrics retrieval after dataset identification.

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 on when to use: after obtaining setIds from cnbs_search or cnbs_fetch_nodes with isEnd=true. It also notes that name filtering is optional and only effective with a single setId. However, it does not explicitly state when not to use the tool.

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 provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds behavioral detail about isEnd=true indicating setIds, which is useful beyond annotations. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a clear Args section and Returns line. It is front-loaded with the purpose and every sentence provides value. 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?

Input schema is simple with no output schema, so the description must explain return values. It states the return is a list of tree nodes, grouped by category for multiple categories, but lacks details on node fields (e.g., id, name, isEnd). This 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?

Schema coverage is 100%, but the description adds significant domain-specific meaning: it explains the numeric code mapping for categories (e.g., '3' for 年度) and clarifies that parentId is only effective for single categories, going beyond the schema descriptions.

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 fetches CNBS classification tree nodes, with specific verb 'fetch' and resource 'nodes'. It distinguishes itself from siblings like cnbs_fetch_end_nodes by supporting multiple categories and explaining that nodes with isEnd=true are setIds.

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 support for multiple categories and that parentId is only effective for a single category, but does not explicitly contrast with siblings like cnbs_fetch_end_nodes or provide when-to-use vs alternatives. Usage context is implied but not clearly bounded.

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, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds that it returns a list of data points, which is useful but not extensive. It does not mention rate limits or error handling.

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 well-structured with a summary sentence followed by an Args list and Returns. It is front-loaded and uses clear formatting, though it could be slightly more concise by avoiding duplication of schema 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?

With no output schema, the description only vaguely mentions '统计数据点列表' (list of statistical data points). It does not describe the structure of each data point, how pagination works, or what errors may occur. This is insufficient for an agent to fully understand the return format.

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 input schema already documents all parameters adequately. The tool description mostly repeats the same information without adding new semantic details or usage nuances.

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 '批量获取统计指标数据' (batch fetch statistical indicator data) and specifies support for multiple metric IDs, time periods, and areas. However, it does not differentiate from sibling tools like cnbs_fetch_metrics or cnbs_search, leaving room for confusion.

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 support for multiple IDs, periods, and areas, providing context on when to use the tool. However, it lacks explicit guidance on when not to use it or alternatives among the many 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, destructiveHint=false, idempotentHint=true. The description adds value by listing example return values and clarifying that the tool returns all categories. It does not contradict 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 very concise: one short sentence about purpose plus example returns. No fluff, front-loaded with the main action. Every sentence contributes.

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 tool with no parameters and good annotations, the description is fairly complete. It explains the output structure with examples. Minor gap: it does not mention if the output is sorted or any ordering, but examples suffice.

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 no parameters, so the input schema provides no meaning. The description compensates by explaining what the output contains, including example categories, which adds semantic value 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 clearly states the tool gets all category information including code, name, and time granularity. It provides example return values, making the purpose unambiguous. It distinguishes from siblings like cnbs_fetch_nodes or cnbs_get_regions by focusing on categories.

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 guidance on when to use this tool versus alternatives. It does not mention any prerequisites, when it is appropriate to call it, or when to use other tools instead.

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 read-only, non-destructive, and idempotent. Description adds that the guide includes tool list and tips, fully disclosing behavior without contradiction.

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 purpose, then usage recommendation. Every word is essential.

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

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

For a zero-parameter, read-only guide tool with annotations, the description fully covers what the tool does and when to use it.

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?

No parameters exist; baseline 4 applies. Description correctly omits parameter details as none are 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 it retrieves a usage guide including tool list, suggestions, and tips, which is specific and distinguishable from sibling 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?

Explicitly recommends use on first access, providing clear context. No explicit exclusions, but the guide's nature makes usage straightforward.

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?

Description adds behavioral details beyond annotations: explains return fields (code, name, shortName), shows filtering behavior (e.g., keyword='江' returns provinces with '江'), and default behavior (returns all provinces with no params). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with Args, Returns, and Examples sections. Slightly verbose but clear and front-loaded with purpose.

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?

Tool is simple with only two optional params; description covers purpose, parameters, examples, and return structure completely. No output schema 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?

Schema has 100% coverage with descriptions, but description adds examples and clarifies default behavior (no params returns provinces), which is not in 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?

Description states '获取可用的地区列表' (get available region list) and explains filtering by keyword and level, distinguishing it from sibling tools like cnbs_search which search for data.

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

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

Provides examples of usage (no params, keyword filters), but does not explicitly say when to use this tool vs alternatives. However, context from sibling tools makes it clear.

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, destructiveHint=false, and idempotentHint=true. The description adds minimal behavioral context beyond stating it returns category information, which 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 concise, well-structured with clear sections (Args, Returns, examples), and every sentence serves a purpose. No unnecessary text.

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 one parameter and no output schema, the description covers the essential purpose and usage. However, it lacks detail on the return format or structure, which could aid the 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?

The input schema has 100% coverage with parameter description. The description adds value by providing concrete example values for the 'source' parameter (census, international, department), which are not in 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 clearly states the tool gets category information for a specific data source, using a specific verb and resource. However, it does not differentiate from sibling tools like cnbs_get_categories, relying on the tool name's 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?

Examples are provided for valid source values, implying usage context. But there is no explicit guidance on when to use this tool versus alternatives (e.g., cnbs_get_categories), or when not to use 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is clear. The description adds value by specifying the return content (name, description, status) beyond what annotations provide, but it does not cover any potential limitations like pagination or performance.

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: three sentences covering purpose, return value, and an example. Every sentence is necessary 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?

Given the absence of parameters and output schema, the description is adequately complete. It explains what the tool does and what it returns. A minor gap is that it does not mention typical use cases or that this tool is for discovery before using other data-fetching tools.

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?

With zero parameters, the baseline is 4. The description correctly adds no parameter details since none exist, and the schema already covers 100% of 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 verb '列出' (list) clearly specifies the action on the resource '数据源' (data sources). It distinguishes itself from sibling tools like cnbs_fetch_data_from_source or cnbs_search, which operate on specific sources or search within them, by indicating it lists all available sources.

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 as a starting point to discover available data sources, but it does not explicitly state when or when not to use this tool or mention alternatives. For example, it could clarify that this is for browsing all sources before narrowing down with 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?

Annotations (readOnlyHint=true, destructiveHint=false, idempotentHint=true) already inform safe read-only behavior. The description adds return structure details but no extra behavioral disclosures like pagination limits or rate constraints. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an intro, Args list, and Returns. It is front-loaded with the search purpose. The Args section is slightly redundant with the schema, but overall concise for 7 parameters.

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 7 parameters, a nested object, and no output schema, the description covers essential aspects: tool function, parameter purposes (both in text and schema), and return format. Lacks search behavior specifics (e.g., fuzzy matching) but sufficient for a search 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%, so the baseline is 3. The description lists parameters with their meanings, largely repeating schema descriptions. It adds minor value by organizing and emphasizing 'keyword' as required, but does not significantly enhance understanding beyond 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 clearly states it searches CNBS data by keyword, returns dataset list with setId, name, time range. It includes '推荐优先使用' (recommended priority use), distinguishing it from siblings like cnbs_search_in_source and cnbs_batch_search.

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 recommends this tool as the primary search ('推荐优先使用'), giving clear context. However, it does not explicitly mention when not to use it or name alternative tools like cnbs_search_in_source or cnbs_batch_search.

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 indicate read-only, non-destructive, idempotent behavior. The description adds no new behavioral context such as result format, pagination, or error handling.

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 and front-loaded with purpose. The docstring format is slightly redundant (Args/Returns) but overall efficient.

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?

No output schema and the return description is vague. Given sibling tools, the description lacks clarity on scope and limitations. Somewhat 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?

Schema coverage is 100%, so baseline is 3. The description provides example values for 'source' which adds some meaning, but does not detail constraints or format for 'keyword'.

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 the tool searches within a specific data source, which is clear and uses a verb+resource structure. However, it does not explicitly differentiate from siblings like 'cnbs_search' or 'cnbs_batch_search'.

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 on when to use this tool versus alternatives. Examples are provided but they only show parameter values without explaining selection criteria.

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 provide readOnly, idempotent, and openWorld hints. The description reinforces these by stating 'completely free, no authentication needed' and adds that multiple countries can be queried simultaneously. No contradictions, and it provides useful behavioral context beyond 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 concise and front-loaded with the main purpose, followed by a structured Args list. However, it fails to include the 'key' parameter in that list, which is an omission that harms completeness without being overly 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?

Given 5 parameters (1 required), no output schema, and good annotations, the description covers the core functionality and free/no-auth context. However, the missing 'key' parameter and lack of detail on pagination or date format prevent it from being fully complete 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 coverage is 100%, so baseline is 3. The description explains most parameters with examples, defaults, and preset datasets. However, it omits the 'key' parameter entirely, which is present in the schema but not mentioned in the Args list, slightly reducing comprehensiveness.

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 queries BIS statistics, lists specific indicators (effective exchange rates, credit gaps, etc.), and mentions multi-country support. It distinguishes from sibling tools by explicitly naming 'BIS' versus other data sources like IMF, World Bank, etc.

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 use for BIS data via its name and domain, and adds context that it is free and requires no authentication. However, it does not explicitly state when not to use it or name alternative tools for other data sources, though the sibling list makes this implicit.

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 provide readOnlyHint, destructiveHint, idempotentHint. The description adds that it lists 'preset datasets and key templates', but no additional behavioral context. No contradiction.

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?

Single sentence with clear purpose. Efficient, though could be slightly more structured with bullet points.

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?

No output schema, but the description explains what is returned (datasets and key templates). Lacks detail on return format or pagination, adequate for a simple list 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% with one optional parameter 'keyword' described as 'filter by keyword'. The description adds no extra 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 clearly states it lists all preset datasets and key templates from the BIS data source, using a specific verb ('list') and resource. It distinguishes from siblings like ext_oecd_datasets by specifying BIS.

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 on when to use this tool versus other ext_* list tools. No mention of filtering (though a keyword parameter exists) or comparison to alternatives.

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, destructiveHint=false, idempotentHint=true, openWorldHint=true. Description adds '通过 NBS 官方 API 获取真实数据' confirming read-only nature, but no additional behavioral traits like rate limits or data freshness. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise: one sentence for purpose, then parameter list. Every sentence adds value, front-loaded with purpose. 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?

Covers purpose and all parameters adequately. Lacks description of output format or return structure, but openWorldHint suggests completeness not required. For a data retrieval tool, a note on expected output would improve completeness, but not essential.

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 descriptions in Chinese that match the parameter list in the description. Description adds minor context: for keyword it says '覆盖默认' (overrides default), for pageSize it states default 20. Baseline 3 is appropriate as schema does most of the work.

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?

States it queries China NBS census data (population, economic, agriculture) via official API. Clear verb '查询' and resource '普查数据', distinguishing it from sibling tools like ext_fred or cnbs_search that handle other data sources.

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. Implied by name and description that it is for Chinese census data, but no when-not-to-use or comparison with similar tools like cnbs_search.

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 indicate read-only, non-destructive, idempotent behavior. The description adds behavioral traits like fetchAll being slow and indicator defaulting to first keyword, providing additional transparency beyond 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 structured with a header, parameter list, and department enumeration. It is concise and informative, though slightly longer due to the list, but every sentence adds value.

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 lacks information about the output format or structure, which is important since no output schema is provided. It adequately covers input parameters and basic behavior but not the return data.

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 high. The description adds context by listing valid department keys and explaining the behavior of optional parameters (indicator, fetchAll), which adds 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 clearly states it queries department statistics from the National Bureau of Statistics, covering multiple fields. It uses a specific verb 'query' and identifies the resource, and the list of departments distinguishes it from sibling tools like ext_cn_census or ext_cn_department_list.

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 parameter usage details (optional indicator, default values, slow fetchAll) but does not explicitly state when to use this tool versus alternatives. It implies usage context but lacks direct comparisons.

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 provide readOnlyHint and idempotentHint. The description adds that it lists 'all queryable' departments, clarifying the scope. No contradictions, but no additional behavioral detail beyond 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 a single clear sentence, front-loaded with the core purpose, with 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?

For a simple listing tool with no parameters and adequate annotations, the description is complete. It could optionally mention the return format or ordering, but it is sufficient.

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?

No parameters exist, and schema coverage is 100%. The description is not required to add parameter details, and the baseline of 4 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 'List all queryable departments and their indicator keyword lists', using a specific verb and resource. It distinguishes itself from sibling tools like ext_cn_department by focusing on listing all departments.

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 on when to use this tool versus alternatives. With many sibling tools, explicit usage conditions or exclusions would help, but they are absent.

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?

注解已声明只读、幂等特性，描述额外提供了API密钥配置要求，这是有用的行为信息。但未提及响应格式、速率限制或常见错误，附加值一般。

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?

描述结构清晰：先陈述目的，后给出API密钥警告，再列出参数及示例，最后补充常用系列列表。内容精炼，无冗余，每个部分都有价值。

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?

对于5个参数的工具，描述覆盖了参数细节和API密钥，但缺少输出片段的描述（无输出模式），也没有说明错误处理或限制。尽管注解补充了部分内容，但整体完整性仍有欠缺。

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?

模式描述覆盖率为100%，基线为3。描述在参数示例、常用系列列表和日期格式方面增加了超出模式的实用指导，尤其是series参数的说明和常见系列列举，提升了可用性。

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?

描述明确说明工具用于查询FRED经济数据库，涵盖800k+系列，并支持多系列查询。虽然很清晰，但未与同级工具ext_fred_series进行区分，因此减1分。

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?

描述未提供何时使用此工具而非其他数据源（如ext_imf、ext_oecd）的指导，也没有说明不适用的情况。缺乏使用上下文或替代方案比较。

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 indicate read-only, non-destructive, idempotent behavior. Description adds content types (利率、汇率等) but does not disclose pagination, result limits, or other behavioral details beyond 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?

Single concise sentence in Chinese, no redundant words. Front-loaded with tool purpose and scope.

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 simple schema (1 optional param, no output schema) and clear annotations, description sufficiently covers purpose and content types. Could mention the return format or whether series are paginated, but overall complete for a list endpoint.

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 keyword parameter already described as '按关键词过滤'. Description does not add further semantics beyond filtering; 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?

Description clearly states the tool lists all preset series from FRED data source (interest rates, exchange rates, commodities, macroeconomics). Verb '列出' (list) and resource 'FRED 系列' are specific and distinct from siblings like ext_fred (which likely fetches data).

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?

Description implies usage for browsing available series but does not explicitly state when to use this tool versus alternatives (e.g., ext_fred or search tools). No when-not-to-use or exclusion criteria provided.

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, destructiveHint, idempotentHint, and openWorldHint, covering safety. The description adds the key behavioral trait of simultaneously fetching from two sources, which is beyond what annotations provide. No contradiction.

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 consists of one purposeful sentence and a structured Args list. Every element adds value without redundancy or unnecessary length.

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 no output schema, the description lacks details on the return format or structure. It mentions fetching data but not whether results are merged or how errors from one source are handled. This leaves the agent guessing about the output, reducing 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%, providing baseline 3. The description adds value by noting that omitting imfIndicator queries only World Bank, and specifying ISO3 codes for countries. These details supplement the schema descriptions.

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 fetches multi-country data for the same indicator from both World Bank and IMF, enabling quick international comparison. This distinguishes it from individual source tools like ext_world_bank and ext_imf, which lack cross-source comparison.

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 (when needing cross-source comparison for the same indicator), but does not provide explicit guidance on when not to use it or mention alternative tools like individual source tools. Usage context is clear but not comprehensive.

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 provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds value by stating '完全免费，无需认证' (completely free, no authentication), which is behavioral context beyond annotations. No contradiction detected.

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 front-loaded purpose statement and structured 'Args:' section. Every sentence is informative, and there is no redundant information. It efficiently uses both Chinese and English to cover key points.

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 does not explain the return format or structure of the query results. While the input parameters and behavior are well-covered, the lack of output details leaves the agent uncertain about what to expect from the response.

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?

With 100% schema description coverage, the description still adds significant value by providing usage examples (e.g., '["GDP_GROWTH","CPI_INFLATION"]') and a comprehensive list of common indicators. This helps the agent select valid parameter values beyond the schema's generic descriptions.

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 explicitly states it queries IMF World Economic Outlook (WEO) data and lists specific supported indicators. The verb '查询' (query) and resource 'IMF 世界经济展望 (WEO) 数据' are clear. It differentiates from siblings like ext_fred or ext_world_bank by specifying the IMF source, though not explicitly distinguishing from other IMF 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 provides context (free, no auth, supports multiple indicators) but does not explicitly state when to use this tool over alternatives like ext_fred or ext_world_bank. Usage is implied for IMF data queries, but no exclusions or when-not-to-use guidance is given.

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, destructiveHint, idempotentHint, and openWorldHint. The description adds that it directly calls the IMF API, specifying the external source. This goes beyond annotations but still lacks details like response size or potential delays.

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 short sentence that is front-loaded with the core purpose. No unnecessary words; every part adds value.

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 (no parameters, strong annotations, no output schema), the description is fully adequate. It tells the agent exactly what the tool does and its external dependency.

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 no parameters, so the schema provides full coverage. The description is not required to add parameter information. A baseline score of 4 is appropriate for a zero-parameter tool.

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 the complete indicator catalog from IMF DataMapper, using a specific verb ('获取') and resource ('完整指标目录'). It distinguishes itself from sibling tools like ext_imf_indicators by indicating it returns all indicators.

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 vs alternatives (e.g., ext_imf_indicators). The description only mentions it calls the IMF API directly without any context about prerequisites, limitations, or use cases.

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 it read-only, non-destructive, and idempotent. The description adds no behavioral context beyond that.

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?

A single, concise sentence. It is efficient but could benefit from more structure or 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?

No output schema is provided, and the description does not explain what the output looks like. Additionally, it lacks context on how this tool relates to similar 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 coverage is 100% with a single optional 'keyword' parameter described. The description does not add any additional meaning beyond the schema's 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 clearly states it lists all preset indicators. However, it does not differentiate from the sibling tool 'ext_imf_all_indicators', which likely has similar functionality.

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 on when to use this tool versus alternatives like 'ext_imf_all_indicators' or other similar listing tools. The description only states what it does.

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 and idempotentHint; the description adds value by stating it is free, requires no authentication, and warns about potential large data volume when using default key, which are useful behavioral traits beyond metadata.

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 well-structured with an Args section and a preset dataset list, but it partially repeats information already in the schema (parameter descriptions), making it slightly less concise.

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 does not explain the return format or structure of the query results; given there is no output schema, this omission leaves agents without guidance on how to interpret the response.

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 supplements the 100% schema-covered parameters with examples, preset dataset names, and notes on default behavior (e.g., 'all' key may return large data), adding meaning beyond the schema descriptions.

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 queries OECD statistics (SDMX-JSON) and lists supported datasets, distinguishing it from the sibling tool ext_oecd_datasets which likely lists datasets rather than querying data.

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 (free, no authentication) and examples of dataset usage, but lacks explicit guidance on when to use this tool versus other external data tools like ext_imf or ext_fred.

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 indicate read-only, non-destructive, idempotent behavior. The description adds no additional behavioral context (e.g., pagination, rate limits). With annotations present, a 3 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?

Single sentence in Chinese, no wasted words. Front-loaded with purpose. Appropriate for a simple tool.

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, but without an output schema, the description could hint at return format (e.g., dataset names, IDs). It does not, leaving some ambiguity. Still, it is mostly complete for listing datasets.

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%; the description adds no extra meaning beyond the schema. Baseline 3 is adequate as the parameter is optional and has its own 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 clearly states the tool lists all pre-built datasets from the OECD data source. The verb 'list' and resource 'datasets' are specific, and the name distinguishes it from sibling tools like 'ext_oecd'.

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 on when to use this tool versus alternatives (e.g., 'ext_oecd' for actual data). It does not mention when not to use it or provide context on filtering.

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 declare readOnlyHint and idempotentHint, but the description adds that the tool is '完全免费，无需认证' (completely free, no authentication required), which is beyond annotations. This clarifies access requirements and cost, enhancing 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 concise: a short introductory sentence, clear parameter definitions with defaults, and a list of common indicators. No redundant information, and the structure is 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 description lacks details about the return format or data structure, which is not covered by an output schema. While it includes common indicators and defaults, an agent may need to know the shape of the response to use the tool effectively.

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?

All 4 parameters are described both in the schema and in the description. The description adds value by explaining that indicator can be a common name or WB code, countries are ISO3 codes with defaults, and provides a list of common indicators for reference.

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 '查询世界银行开放数据' (query World Bank open data) and specifies supported indicators (GDP, CPI, etc.) and global 200+ countries. It distinguishes itself from sibling tools like ext_world_bank_indicators and ext_world_bank_multi by focusing on data querying with parameters.

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 parameters and lists common indicators but does not provide explicit guidance on when to use this tool versus its siblings. Usage context is implied but not contrasted with alternatives.

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 provide readOnlyHint, destructiveHint, idempotentHint. The description adds that it lists 'all preset indicators,' which aligns with openWorldHint=false but adds minimal behavioral context beyond 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 a single concise sentence in Chinese. It is front-loaded with the action and essential output. Could optionally include more detail, but remains efficient.

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 no output schema, the description adequately describes what is returned (indicators, codes, descriptions). It does not mention pagination or limits, but the tool's simplicity makes this acceptable.

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 one optional parameter with a description in Chinese, covering 100% of parameters. The tool description does not mention the parameter, so it adds no 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 clearly states the tool's action (listing indicators), the data source (World Bank), and what is included (codes and descriptions). It distinguishes from siblings like ext_world_bank (likely for fetching data) and ext_world_bank_multi.

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, such as ext_world_bank. The purpose implies it is for discovering available indicators before querying data, but this is 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true, indicating a safe read operation. The description adds no behavioral traits beyond that, such as rate limits or error behavior. It does not contradict annotations, so baseline of 3 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 concise: a one-line Chinese summary followed by a structured docstring listing parameters. It is front-loaded and avoids unnecessary detail. The docstring format is slightly redundant with the schema but still efficient.

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 moderate complexity (multi-indicator, multi-country), the description covers query intent and parameter semantics well. However, it lacks information about the return format (since no output schema exists) and any limitations or pagination. It is adequate but could be more 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?

Schema description coverage is 100%, so baseline is 3. The description adds value by providing realistic examples for indicators (e.g., 'GDP_GROWTH', 'CPI') and countries (e.g., 'CHN', 'USA'), and clarifying that countries use ISO3 codes. This practical guidance raises the score to 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 clearly states the tool queries multiple World Bank indicators simultaneously and enables cross-country comparison. The verb 'query' and resource 'multiple World Bank indicators' are specific, and it distinguishes from siblings like ext_world_bank (single indicator) and ext_world_bank_indicators (list indicators).

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 (multi-indicator, cross-country queries) via the title and summary, and provides detailed argument examples. However, it does not explicitly state when not to use or mention alternatives like ext_world_bank for single indicators, which would improve guidance.

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