Server Quality Checklist

Tool Scores

• feishu_add_bitable_recordsC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states this is an 'add' operation (implying mutation/write) but doesn't disclose important behavioral aspects: whether this requires specific permissions, what happens on duplicate records, whether there are rate limits, what the response format looks like, or if there are size limits for the records array. For a write operation with zero annotation coverage, this is insufficient.

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

  Conciseness5/5

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

  The description is extremely concise - just two short sentences that communicate the core purpose and one critical constraint. Every word earns its place with no redundancy or filler. The information is front-loaded with the main action stated first.

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

  Completeness2/5

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

  For a write operation with 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what happens after adding records (success/failure responses), doesn't mention error conditions, and provides minimal behavioral context. The description should do more to compensate for the lack of structured metadata, especially for a mutation tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds one useful constraint: '字段名需与表格字段名一致' (field names must match table field names), which provides important semantic context beyond the schema's technical description. However, this is the only parameter guidance provided, so it meets but doesn't exceed the baseline expectation.

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

  Purpose4/5

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

  The description clearly states the action ('向飞书多维表格添加记录' - add records to Feishu Bitable) and resource ('飞书多维表格' - Feishu Bitable), making the purpose immediately understandable. It distinguishes from siblings like feishu_create_bitable (create table) and feishu_read_bitable (read table). However, it doesn't specify whether this adds single or multiple records, which could be more precise.

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

  Usage Guidelines2/5

  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 doesn't mention when to choose this over feishu_write_spreadsheet (for spreadsheets) or feishu_create_bitable (for creating new tables). There's also no mention of prerequisites like authentication requirements or permissions needed to add records.

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

• feishu_get_document_infoC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves basic information, implying a read-only operation, but doesn't specify whether it requires authentication, has rate limits, what happens with invalid document IDs, or the format of the returned information. For a tool with zero annotation coverage, this leaves significant behavioral gaps, though it correctly implies a safe read operation.

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

  Conciseness4/5

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

  The description is a single, efficient sentence in Chinese that directly states the purpose and examples of retrieved information. It's appropriately sized for a simple tool with one parameter and no complex behavior. However, it could be slightly more front-loaded by explicitly stating it's for metadata retrieval to distinguish from content reading tools.

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

  Completeness3/5

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

  Given the tool's low complexity (one parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on usage context, behavioral traits, and output format. For a read-only tool with no annotations, it should ideally mention authentication needs or error handling to be more complete, but it's not entirely inadequate for such a simple operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100% (the single parameter 'document_id' is fully described in the schema as '飞书文档 ID 或 URL' - Feishu document ID or URL). The description adds no additional parameter information beyond what the schema provides, such as examples or constraints. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '获取飞书文档的基本信息' (get basic information of a Feishu document) with specific examples of what information is retrieved ('包括标题、ID、版本号等' - including title, ID, version number, etc.). It distinguishes itself from siblings like feishu_read_document (which likely reads content) and feishu_create_document (which creates documents), though it doesn't explicitly name these alternatives. The verb '获取' (get/retrieve) and resource '飞书文档的基本信息' (basic information of Feishu document) are specific.

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

  Usage Guidelines2/5

  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 doesn't mention when this tool is appropriate (e.g., for metadata only vs. content reading with feishu_read_document) or any prerequisites. While the purpose is clear, there's no explicit context for usage decisions among the sibling tools listed.

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

• feishu_read_spreadsheetC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It mentions what the tool does (reads data from specified range) but lacks critical behavioral details: authentication requirements, rate limits, error handling, return format (structure of returned data), pagination for large ranges, or whether it's a safe read-only operation. The description is minimal and doesn't compensate for the absence of annotations.

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

  Conciseness4/5

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

  The description is extremely concise (two short sentences) with zero wasted words. It's front-loaded with the core purpose and follows with the return behavior. However, this conciseness comes at the cost of completeness - it's arguably too brief for a tool with no annotations and no output schema.

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

  Completeness2/5

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

  Given the complexity of spreadsheet operations, absence of annotations, and lack of output schema, the description is insufficiently complete. It doesn't explain what format the data returns in (array of arrays? JSON objects?), how authentication works, error conditions, or performance characteristics. For a data retrieval tool with no structured output definition, the description should provide more context about the return value.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema - it mentions '指定范围' (specified range) which is already covered by the 'range' parameter description. With complete schema coverage, the baseline score of 3 is appropriate as the description doesn't add value beyond the structured schema.

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

  Purpose4/5

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

  The description clearly states the action ('读取数据' - read data) and resource ('飞书电子表格' - Feishu spreadsheet), making the purpose immediately understandable. It distinguishes from siblings like 'feishu_write_spreadsheet' by specifying read vs write operations. However, it doesn't explicitly differentiate from 'feishu_read_bitable' or 'feishu_read_document' which are also read operations on different Feishu resources.

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

  Usage Guidelines2/5

  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 doesn't mention when to choose this over 'feishu_read_bitable' (for reading database-like tables) or 'feishu_read_document' (for reading document content), nor does it specify prerequisites like authentication requirements or spreadsheet access permissions.

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

• feishu_write_spreadsheetC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a write operation but doesn't mention important behavioral aspects: whether this overwrites existing data or appends, what permissions are required, error conditions, rate limits, or what happens when ranges don't match data dimensions. The description only covers basic functionality without operational context.

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

  Conciseness5/5

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

  The description is extremely concise with just two sentences that directly state the core functionality and key capabilities. Every word earns its place with zero waste or redundancy. It's front-loaded with the primary purpose and efficiently communicates the essential features.

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

  Completeness2/5

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

  For a write operation tool with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns, error handling, data format requirements beyond '二维数组数据', or how it interacts with existing spreadsheet content. The description leaves too many operational questions unanswered for a mutation tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so all parameters are documented in the schema. The description adds minimal value beyond the schema by mentioning support for specifying worksheets and ranges, but doesn't provide additional semantic context about parameter interactions, default behaviors, or practical examples. The baseline of 3 is appropriate since the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the action ('写入数据' - write data) and target resource ('飞书电子表格' - Feishu spreadsheet), making the purpose immediately understandable. It distinguishes from sibling tools like feishu_read_spreadsheet by specifying write vs. read operations. However, it doesn't explicitly differentiate from other write operations like feishu_append_content or feishu_update_content.

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

  Usage Guidelines2/5

  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. While it mentions support for specifying worksheets and ranges, it doesn't explain when this write operation is appropriate compared to feishu_append_content, feishu_update_content, or other data manipulation tools in the sibling list. There's no mention of prerequisites, limitations, or typical use cases.

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

• feishu_create_bitableB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden. It mentions the return values (app_token and URL), which is helpful, but lacks critical behavioral details: permission requirements, whether creation is idempotent, rate limits, error conditions, or what happens if the folder_token is invalid. For a creation tool with zero annotation coverage, this is insufficient.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that front-loads the core action and includes return values. Every word earns its place with no redundancy or unnecessary elaboration.

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

  Completeness3/5

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

  Given no annotations and no output schema, the description partially compensates by stating return values, but it misses key context for a creation tool: authentication needs, error handling, or interaction with siblings (e.g., feishu_add_bitable_records for populating the table). It's minimally adequate but has clear gaps.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents both parameters (name and folder_token) with descriptions. The description adds no additional parameter semantics beyond what's in the schema, such as format examples or constraints. Baseline 3 is appropriate when schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the action ('创建新的' - create new) and resource ('飞书多维表格' - Feishu Bitable), making the purpose explicit. It distinguishes from siblings like feishu_create_document or feishu_create_spreadsheet by specifying the Bitable type. However, it doesn't explicitly differentiate from all siblings (e.g., feishu_add_bitable_records adds to existing tables).

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., needing folder access), compare with similar tools like feishu_create_spreadsheet, or specify use cases (e.g., initial setup vs. adding records).

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

• feishu_create_spreadsheetB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a spreadsheet and returns a token and URL, which implies a write operation, but lacks details on permissions needed, rate limits, error handling, or whether the creation is reversible. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

  Conciseness5/5

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

  The description is extremely concise with two sentences that directly state the purpose and return values, with zero wasted words. It's front-loaded with the core action and efficiently communicates essential information without redundancy.

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

  Completeness3/5

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

  Given the tool creates a resource (moderate complexity), has no annotations, and no output schema, the description is minimally adequate. It covers the basic action and return values but lacks behavioral context and usage guidance. For a mutation tool, this leaves gaps in understanding permissions and error handling, making it just viable but incomplete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100%, with both parameters (title and folder_token) well-documented in the schema. The description adds no parameter-specific information beyond what the schema provides, such as examples or constraints. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the action ('创建新的飞书电子表格' - create new Feishu spreadsheet) and resource, with a specific verb and resource type. It distinguishes from siblings like feishu_read_spreadsheet (read vs. create) and feishu_write_spreadsheet (write to existing vs. create new), though not explicitly named. However, it doesn't fully differentiate from feishu_create_document or feishu_create_bitable which also create resources, missing a 5.

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

  Usage Guidelines2/5

  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 doesn't mention when to choose this over feishu_create_document or feishu_create_bitable for different document types, nor does it specify prerequisites or exclusions. This leaves the agent without context for tool selection among creation tools.

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

• feishu_insert_calloutB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states this is an insertion operation ('插入'), implying mutation, but doesn't mention permissions needed, whether the operation is idempotent, error conditions, or what happens on success/failure. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.

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

  Conciseness4/5

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

  The description is appropriately concise - two sentences that state the tool's purpose and usage context. It's front-loaded with the core functionality. However, the second sentence could be more specific about the callout's purpose rather than listing generic examples.

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

  Completeness2/5

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

  For a mutation tool with 6 parameters, no annotations, and no output schema, the description is insufficient. It doesn't cover behavioral aspects like error handling, permissions, or what the tool returns. While the schema covers parameters well, the description lacks critical context needed for safe and effective tool invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions '高亮块' (callout block) which relates to the tool's purpose but doesn't provide additional context about parameter usage or interactions.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: '在飞书文档中插入高亮块（Callout）' (inserts a callout block in Feishu documents). It specifies the verb ('插入' - insert) and resource ('飞书文档' - Feishu document), and distinguishes from siblings by mentioning '高亮块' (callout block) rather than other content types like tables or images. However, it doesn't explicitly differentiate from similar tools like 'feishu_append_content' or 'feishu_update_content'.

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

  Usage Guidelines3/5

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

  The description provides some usage context: '用于突出显示提示、警告、注意事项等信息' (used to highlight tips, warnings, notes, etc.). This implies when to use it (for highlighting information) but doesn't explicitly state when NOT to use it or mention alternatives among sibling tools. No guidance on prerequisites or constraints is provided.

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

• feishu_read_bitableB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the return format ('Markdown 格式的表格' meaning 'Markdown format table') which is valuable context, but doesn't address important behavioral aspects like whether this is a read-only operation (implied but not stated), authentication requirements, rate limits, pagination behavior (though 'page_size' parameter hints at it), or error conditions. For a tool with zero annotation coverage, this leaves significant gaps.

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

  Conciseness5/5

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

  The description is extremely concise - a single sentence that efficiently communicates the core functionality and output format. Every word earns its place with no wasted text. It's appropriately sized for the tool's complexity and gets straight to the point.

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

  Completeness3/5

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

  Given the tool has 3 parameters with full schema coverage but no annotations and no output schema, the description provides the basic purpose and output format. However, for a data retrieval tool that presumably interacts with an external API, it should ideally mention authentication requirements, rate limits, or error handling. The return format information is helpful, but without an output schema, more detail about the structure of returned data would be beneficial.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100%, meaning all parameters are documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema (app_token, table_id, page_size with their descriptions). According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter info in the description, which applies here.

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

  Purpose4/5

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

  The description clearly states the action ('读取' meaning 'read') and resource ('飞书多维表格的记录' meaning 'Feishu multi-dimensional table records'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'feishu_read_document' or 'feishu_read_spreadsheet' which also read different Feishu resources, so it doesn't reach the highest level of sibling differentiation.

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

  Usage Guidelines2/5

  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. With multiple sibling tools that read different Feishu resources (documents, spreadsheets), there's no indication of when this specific table-reading tool is appropriate versus other read operations. No context, exclusions, or alternatives are mentioned.

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

• feishu_append_contentB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool appends content and supports Markdown format, but doesn't mention important behavioral aspects: whether this requires specific permissions, whether the operation is idempotent, what happens on failure, rate limits, or what the response looks like (success/failure indicators). For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

  Conciseness5/5

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

  The description is extremely concise with just two sentences that directly address the tool's purpose and key capability (Markdown support). Every word earns its place - no redundant information, no unnecessary elaboration. The structure is front-loaded with the core purpose followed by important format details.

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

  Completeness2/5

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

  Given this is a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't address critical contextual information: what permissions are needed, whether the operation is reversible, what happens if the document doesn't exist, what the return value contains, or error conditions. For a tool that modifies documents, this leaves significant gaps in understanding how to use it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, with both parameters clearly documented in the schema. The description adds minimal value beyond the schema: it reinforces that content supports Markdown format (already in schema) and implies document_id refers to Feishu documents (implied by tool name). No additional syntax, format details, or constraints beyond what the schema provides are included. Baseline 3 is appropriate when schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the action ('向飞书文档末尾追加内容' - append content to the end of a Feishu document) and specifies the resource (Feishu document). It distinguishes from siblings like feishu_update_content (which likely modifies existing content) and feishu_create_document (which creates new documents). However, it doesn't explicitly contrast with all siblings like feishu_insert_callout or feishu_insert_table, which are more specific insertion operations.

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

  Usage Guidelines3/5

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

  The description implies usage context through '向飞书文档末尾追加内容' (append to end of document), suggesting this is for adding content to existing documents rather than creating new ones or modifying specific sections. However, it lacks explicit guidance on when to use this versus alternatives like feishu_update_content (for modifying existing content) or feishu_insert_* tools (for inserting at specific positions). No exclusion criteria or prerequisites are mentioned.

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

• feishu_insert_imageB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. While it mentions the file token requirement, it doesn't describe what happens on success/failure, whether the operation is idempotent, what permissions are needed, rate limits, or error conditions. For a mutation tool (image insertion) with zero annotation coverage, this represents significant gaps in behavioral transparency.

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

  Conciseness5/5

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

  The description is extremely concise - just two short sentences that directly state the tool's function and key constraint. Every word earns its place with no redundancy or fluff. The information is front-loaded with the primary purpose stated first, followed by the important constraint about file tokens.

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

  Completeness2/5

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

  For a mutation tool with 5 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns, error conditions, authentication requirements, or side effects. While the schema covers parameters well, the overall context for using this tool effectively is incomplete given its complexity and lack of structured metadata.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds minimal value beyond the schema - it mentions file token usage but doesn't provide additional context about parameter interactions, defaults, or constraints. The baseline of 3 is appropriate when the schema does the heavy lifting for parameter documentation.

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

  Purpose4/5

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

  The description clearly states the action ('插入图片' - insert image) and resource ('在飞书文档中' - in Feishu document), making the purpose immediately understandable. It distinguishes from sibling tools like feishu_upload_image (which uploads images) and feishu_append_content (which adds text content). However, it doesn't explicitly contrast with other insertion tools like feishu_insert_table or feishu_insert_diagram.

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

  Usage Guidelines3/5

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

  The description implies usage context by mentioning '支持通过文件 token 插入已上传的图片' (supports inserting already uploaded images via file token), suggesting this tool should be used after feishu_upload_image. However, it doesn't provide explicit guidance on when to choose this tool versus alternatives like feishu_append_content for different content types, nor does it mention any prerequisites or exclusions.

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

• feishu_update_contentB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It discloses that the tool replaces all content while preserving the title, which is a key behavioral trait. However, it lacks details on permissions required, whether the operation is reversible, rate limits, error handling, or what happens to existing formatting/blocks. For a mutation tool with zero annotation coverage, this is a significant gap in behavioral transparency.

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

  Conciseness5/5

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

  The description is extremely concise with two short sentences in Chinese, front-loading the core action ('替换飞书文档的全部内容') and then specifying the use case. There is zero wasted text, and every word earns its place by clarifying the tool's purpose and scope efficiently.

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

  Completeness3/5

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

  Given the tool has 2 parameters with full schema coverage but no annotations and no output schema, the description is minimally adequate. It covers the basic purpose and behavioral aspect of title preservation, but as a mutation tool, it should ideally include more about side effects, permissions, or response format to be fully complete for agent use.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, with clear descriptions for both parameters (document_id and content). The description adds minimal value beyond the schema, only reinforcing that content replaces everything except the title. Since the schema already documents parameters well, the baseline score of 3 is appropriate, as the description doesn't provide additional syntax, format, or constraints information.

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

  Purpose4/5

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

  The description clearly states the verb ('替换' meaning 'replace') and resource ('飞书文档的全部内容' meaning 'all content of Feishu document'), specifying it preserves the title. It distinguishes from siblings like feishu_append_content (which adds content) and feishu_read_document (which reads content). However, it doesn't explicitly differentiate from feishu_delete_block (which might delete content) or other content modification tools, keeping it from a perfect score.

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

  Usage Guidelines3/5

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

  The description implies usage ('用于完全重写文档内容' meaning 'used for completely rewriting document content'), suggesting it's for full content replacement rather than partial updates. However, it doesn't provide explicit when-to-use guidance vs. alternatives like feishu_append_content or feishu_insert_* tools, nor does it mention prerequisites or exclusions, leaving usage context somewhat vague.

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

• feishu_insert_tableB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. It mentions two input formats (Markdown or structured data) but doesn't describe permissions needed, whether the operation is idempotent, error conditions, rate limits, or what happens on success/failure. For a mutation tool with 7 parameters, this leaves significant behavioral gaps.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that immediately states the core functionality. Every word earns its place: it specifies the action, location, and supported input formats without any redundancy or unnecessary elaboration.

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

  Completeness2/5

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

  For a mutation tool with 7 parameters and no annotations or output schema, the description is insufficiently complete. It doesn't address critical contextual information like required permissions, error handling, response format, or how this tool relates to sibling operations. The agent lacks guidance on behavioral expectations beyond the basic functionality statement.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, providing detailed parameter documentation. The description adds marginal value by mentioning the two input format options (Markdown vs structured data), which corresponds to the markdown_table parameter versus headers+rows parameters. However, it doesn't provide additional semantic context beyond what the schema already documents thoroughly.

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

  Purpose5/5

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

  The description clearly states the specific action ('插入表格' - insert table) and resource ('在飞书文档中' - in Feishu document), distinguishing it from sibling tools like feishu_append_content (general content) or feishu_insert_image (different element type). It precisely identifies what the tool does without being tautological.

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

  Usage Guidelines3/5

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

  The description implies usage context through '支持 Markdown 表格语法或结构化数据输入' (supports Markdown table syntax or structured data input), suggesting this tool is for table insertion specifically. However, it doesn't explicitly state when to use this versus alternatives like feishu_create_spreadsheet (for spreadsheet creation) or feishu_write_spreadsheet (for spreadsheet writing), nor does it provide exclusion guidance.

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

• feishu_create_documentA
  3.5/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the creation action and return value (URL), but doesn't describe authentication requirements, rate limits, error conditions, whether the operation is idempotent, or what happens with duplicate titles. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.

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

  Conciseness5/5

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

  The description is extremely concise (one sentence in Chinese) with zero wasted words. It's front-loaded with the core purpose and efficiently covers key aspects: action, parameters (title/content), format (Markdown), and return value (URL). Every element earns its place.

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

  Completeness3/5

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

  For a creation tool with 3 parameters, 100% schema coverage, but no annotations and no output schema, the description is minimally adequate. It covers the basic purpose and return value but lacks behavioral context (permissions, errors, etc.) that would be important for a mutation operation. The absence of output schema means the description should ideally say more about the response structure beyond just 'URL'.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description mentions title and Markdown content but doesn't add meaningful semantics beyond what the schema provides (e.g., examples of Markdown usage, title constraints beyond length). The folder_token parameter isn't mentioned at all in the description. Baseline 3 is appropriate when schema does the heavy lifting.

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

  Purpose5/5

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

  The description clearly states the specific action ('创建新的飞书文档' - create new Feishu document), the resources involved (document with title and Markdown content), and distinguishes it from siblings like feishu_read_document (read) and feishu_update_content (update). It explicitly mentions the return value (URL), which helps differentiate from other creation tools like feishu_create_bitable or feishu_create_spreadsheet.

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

  Usage Guidelines3/5

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

  The description implies usage context (creating new documents with Markdown content) but doesn't explicitly state when to use this versus alternatives like feishu_append_content (for adding to existing documents) or feishu_update_content (for modifying existing content). No guidance is provided about prerequisites, permissions, or when not to use this tool.

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

• feishu_insert_diagramA
  3.5/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('插入' - insert) which implies a write/mutation operation, but doesn't disclose permissions needed, whether the insertion is reversible, rate limits, or what happens on failure. The mention of '不指定则追加到文档末尾' (if not specified, append to document end) for block_id adds some behavioral context, but significant gaps remain for a mutation tool.

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

  Conciseness5/5

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

  The description is efficiently structured in two sentences: first states the core purpose with specific details, second lists supported diagram types. Every element earns its place with no redundant information. The Chinese text is clear and direct without unnecessary elaboration.

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

  Completeness3/5

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

  For a mutation tool with 3 parameters, 100% schema coverage, but no annotations and no output schema, the description provides adequate purpose and parameter coverage but lacks behavioral context. It doesn't explain what the tool returns, error conditions, or mutation implications. The completeness is minimal viable given the structured data available.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema - it mentions Mermaid code and diagram types but doesn't provide additional syntax, format, or usage details. With complete schema coverage, baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the specific action ('插入' - insert), target resource ('飞书文档中' - in Feishu document), and content type ('Mermaid 架构图' - Mermaid diagram). It distinguishes from sibling tools by specifying it's for diagrams using Feishu's '文本绘图' feature, unlike other insertion tools like feishu_insert_image, feishu_insert_table, or feishu_insert_callout.

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

  Usage Guidelines3/5

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

  The description implies usage context by mentioning '使用飞书「文本绘图」功能' (using Feishu's 'text drawing' feature) and listing supported diagram types, but doesn't explicitly state when to use this tool versus alternatives like feishu_insert_image for non-Mermaid diagrams or feishu_append_content for general text. No explicit exclusions or prerequisites are provided.

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

• feishu_list_blocksA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool lists Blocks and can be used to get Block IDs, it doesn't describe important behavioral aspects: whether this is a read-only operation, what format the output returns, whether there are pagination considerations, rate limits, or authentication requirements. For a tool with zero annotation coverage, this represents significant gaps in behavioral transparency.

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

  Conciseness5/5

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

  The description is extremely concise with just one sentence that efficiently communicates both the tool's purpose and its usage context. Every word earns its place, and the information is front-loaded with no unnecessary elaboration. This represents optimal conciseness for a simple tool.

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

  Completeness3/5

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

  Given the tool's relative simplicity (1 parameter, no annotations, no output schema), the description provides adequate basic information about what the tool does and why to use it. However, it lacks details about the return format and behavioral characteristics that would be important for an AI agent to properly invoke and interpret results from this tool. The description is complete enough for basic understanding but has clear gaps.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100% for the single parameter (document_id), so the schema already documents this parameter completely. The description doesn't add any additional semantic information about parameters beyond what's in the schema. According to scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no parameter information in the description.

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

  Purpose4/5

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

  The description clearly states the action ('列出' - list) and resource ('飞书文档中的所有 Block' - all Blocks in Feishu document), providing a specific verb+resource combination. It distinguishes this tool from siblings like feishu_read_document by focusing on Block-level structure rather than document content. However, it doesn't explicitly contrast with feishu_get_document_info which might also provide structural information.

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

  Usage Guidelines4/5

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

  The description provides clear context for when to use this tool: '用于了解文档结构或获取特定 Block ID 进行后续操作' (for understanding document structure or obtaining specific Block IDs for subsequent operations). This gives practical guidance about the tool's purpose. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the sibling tools.

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

• feishu_read_documentA
  3.7/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden. It states the tool reads content but doesn't disclose behavioral traits like authentication requirements, rate limits, error conditions, or whether it's idempotent. For a tool that accesses external resources, this is a significant gap in transparency.

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

  Conciseness5/5

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

  Two concise sentences with zero waste. First sentence states the core purpose, second sentence covers input options and output formats. Perfectly front-loaded and appropriately sized for this tool's complexity.

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

  Completeness3/5

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

  For a read-only tool with no annotations and no output schema, the description is adequate but has clear gaps. It covers the basic purpose and parameters well, but lacks information about authentication, error handling, rate limits, and what the return structure looks like (beyond format types).

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already fully documents both parameters. The description adds minimal value beyond the schema - it mentions supporting document IDs or URLs and output formats, but the schema already covers these details comprehensively. Baseline 3 is appropriate when schema does the heavy lifting.

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

  Purpose5/5

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

  The description clearly states the action ('读取' - read), target resource ('飞书文档内容' - Feishu document content), and distinguishes from siblings like feishu_get_document_info (which likely returns metadata) and feishu_update_content (which modifies content). It specifies both input types (ID or URL) and output formats (Markdown or JSON).

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

  Usage Guidelines4/5

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

  The description provides clear context for when to use this tool: to read document content in specific formats. It doesn't explicitly mention when NOT to use it or name alternatives, but the sibling tools suggest clear distinctions (e.g., use feishu_get_document_info for metadata, feishu_update_content for modifications).

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

• feishu_upload_imageA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully reveals two critical behavioral traits: 1) the tool returns a file_token (output behavior), and 2) it requires specific permissions ('drive:drive:media:upload'). This provides essential context about authentication requirements and output format that isn't available elsewhere.

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

  Conciseness5/5

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

  The description is extremely efficient - just two sentences that each earn their place. The first sentence states the core purpose, the second provides critical behavioral context (permission requirements). There's zero wasted text, and the warning symbol appropriately highlights the permission requirement.

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

  Completeness4/5

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

  For a 2-parameter upload tool with no annotations and no output schema, the description does well by explaining the key output (file_token) and permission requirements. However, it doesn't mention file size limits, supported formats, error conditions, or whether the upload is synchronous/asynchronous. Given the complexity of file upload operations, there are some behavioral gaps.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any additional meaning about the parameters beyond what's in the schema. It doesn't explain usage patterns, constraints, or relationships between file_path and document_id. The baseline 3 is appropriate when the schema does the heavy lifting.

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

  Purpose5/5

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

  The description clearly states the specific action ('上传图片' - upload image) and target resource ('飞书' - Feishu). It distinguishes itself from sibling tools like 'feishu_insert_image' by explaining it provides the file_token needed for that tool, establishing a clear functional relationship.

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

  Usage Guidelines4/5

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

  The description provides clear context about when to use this tool - to upload images and obtain file_tokens for insertion operations. It explicitly mentions the sibling tool 'feishu_insert_image' as the downstream consumer. However, it doesn't specify when NOT to use it or mention alternative upload methods.

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

• feishu_delete_blockA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well: it discloses the tool's unreliability ('可能无法使用' - may not work), destructive nature ('删除操作不可恢复' - deletion is irreversible in the confirm parameter description), and provides a workaround. However, it doesn't mention authentication needs, rate limits, or error handling specifics.

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

  Conciseness5/5

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

  Two sentences with zero waste: first states the purpose, second provides critical warnings and alternatives. The structure is front-loaded with core functionality followed by essential caveats, making every sentence earn its place.

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

  Completeness4/5

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

  For a destructive tool with no annotations and no output schema, the description is quite complete: it covers purpose, limitations, and alternatives. However, it doesn't explain what happens on success/failure or return values, which would be helpful given the lack of output schema. The high schema coverage helps compensate.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description doesn't add parameter details beyond the schema, but the schema's confirm parameter description includes critical safety context ('删除操作不可恢复' - deletion is irreversible), which aligns with the tool's purpose. This elevates the score slightly as it reinforces behavioral transparency.

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

  Purpose5/5

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

  The description clearly states the specific action ('删除' meaning delete) and resource ('飞书文档中的指定 Block' meaning specified block in Feishu document), distinguishing it from sibling tools like feishu_update_content or feishu_list_blocks. It precisely defines what the tool does without being tautological.

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

  Usage Guidelines5/5

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

  Explicitly provides when-not-to-use guidance: warns that the Feishu API may not support direct block deletion and suggests an alternative approach ('建议通过编辑将块内容清空作为替代方案' - suggests clearing block content via editing as an alternative). This directly addresses when to avoid this tool versus using editing alternatives.

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