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

Describes the full authentication flow (browser launch, login, workspace selection, consent, token storage) and aligns with annotations (destructiveHint=false, openWorldHint=true). Adds valuable 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?

Two concise sentences front-loading the main action, with no wasted words. Efficiently structured.

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

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

For a simple one-parameter tool with no output schema, the description fully covers the authentication process, usage context, and parameter behavior. Complete and 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 description coverage is 100%, and the description's mention of force parameter essentially paraphrases the schema's description. Minimal additional value beyond what schema provides.

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

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

Description clearly states the tool performs OAuth2 authentication to ReportFlow, including browser launch, token storage, and distinct action from siblings which handle downloads and PDF generation.

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 instructs to call this tool first when other tools return authentication errors, and explains when to use force=true for re-authentication. Provides clear context for usage.

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

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

The description discloses that files are saved locally, returns the file path, and handles directory selection. Annotations already indicate idempotency, and the description adds context about default behavior. 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?

Two sentences, front-loaded with the action, no extraneous information. Efficient and complete.

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

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

The description covers the prerequisite, parameters, output, and directory behavior. No output schema needed; the return value is explained. Complete given the tool's complexity.

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

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

Schema coverage is 100%, but the description adds value by explaining the default directory behavior (current working directory) not present in schema. All 4 parameters are well-covered.

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 downloads a single PDF file generated by generate_pdf_async, specifying the required parameters and return value. It distinguishes from the sibling download_zip.

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 that this tool is used after generate_pdf_async and describes the optional outputDir. It does not explicitly exclude cases where download_zip might be preferred, but provides clear context.

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 idempotentHint=true and non-destructive nature. The description adds that it saves to a directory and returns a local path, which is useful but not extensive. 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?

Two sentences, front-loaded with the action, no unnecessary words. 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?

For a simple download tool, the description covers how to use it, what to specify, and what it returns. No output schema, but the return is implied. Could mention that it overwrites existing files, 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%, but the description adds context beyond schema: it explains the behavior of outputDir (saves to current directory if unspecified). This adds value, though fileName is not mentioned.

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 downloads a ZIP file generated by generate_pdfs_async, specifies requestId, and returns a local path. This distinguishes it from siblings like download_file.

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 ties the tool to a specific prior tool (generate_pdfs_async), giving clear context. However, it does not explicitly mention when not to use or list alternatives beyond that association.

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

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

Annotations are minimal (readOnlyHint false, etc.). Description adds that it's async and returns immediately, but lacks details on side effects, idempotency, or error behavior.

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 efficient paragraphs: first states purpose, second gives critical usage guidelines. No redundancy, front-loaded with key info.

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?

Returns requestId and files info are mentioned but not detailed. No output schema, so description could elaborate further on response format or error handling. Links to download_file and get_design_parameters partially compensates.

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 covers all parameters with detailed descriptions. Description adds crucial guidance to check parameter structure with get_design_parameters, adding value 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?

Description clearly states the tool asynchronously generates PDF with design ID and parameters, returns requestId and files info, and distinguishes from sibling tools like download_file and synchronous variants.

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 explicit pre-conditions: must call get_design_parameters, ask user for missing values, avoid placeholder values. Does not mention alternative generation tools (synchronous, batch) that could be compared.

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 readOnlyHint=false (write operation) and destructiveHint=false. The description adds behavioral context: 'Immediately returns requestId and files information,' clarifying the async nature and immediate response. 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 concise, front-loaded with the primary function, and contains no unnecessary words. The important warning section is separate and clearly marked. 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?

Given the tool's complexity (multiple PDFs async), the description covers key aspects: async behavior, immediate return, prerequisite steps, and referral to another tool for ZIP. It lacks detail on the response structure beyond 'requestId and files information,' but this is adequate given no output schema. Annotations and schema fill remaining gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by explaining that the 'params' field should be structured based on get_design_parameters, and it highlights the required 'fileName' and 'params' fields. This guidance is crucial for correct parameter usage.

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

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

The description clearly states the tool's purpose: 'Generates multiple PDFs asynchronously with multiple parameter sets.' It specifies the verb 'generate', the resource 'multiple PDFs', and the asynchronous mode. It also distinguishes from siblings by explicitly mentioning the download_zip tool for ZIP downloads and implying sync versions exist.

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

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

The description provides explicit usage guidelines: before calling, use get_design_parameters to check required parameters, ask the user for missing values, and never generate placeholders. It also directs the user to download_zip for ZIP downloads, offering clear when-to-use versus alternative 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?

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description details synchronous generation, local path return, output directory logic, and shareType mapping. It also warns about not fabricating parameter values, adding behavioral context.

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

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

The description is two paragraphs: first explains functionality and output, second is an important usage note. Every sentence adds value, no redundancy, key information is front-loaded.

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

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

The description covers the tool's core purpose, requirements, output, and configuration options. It could mention potential limitations like file size or error handling, but for its complexity it is sufficiently 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 value by explaining shareType codes and their response mapping, default output directory behavior, and that 'params' should be obtained via get_design_parameters. This goes beyond the raw schema definitions.

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 the tool generates multiple PDFs synchronously from parameter sets and returns a ZIP file. It distinguishes from siblings like generate_pdf_sync (single) and generate_pdfs_async (async) by specifying '一括同期生成' (batch sync generation).

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 prerequisites: always call get_design_parameters first and ask the user for missing values. It warns against using placeholder values. However, it does not explicitly contrast with async tools or state 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.

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

Description adds significant behavioral context beyond annotations: synchronous generation, download URL in response, local save for stdio, no server save for HTTP, optional inline preview. No contradictions with annotations (readOnlyHint=false, destructiveHint=false).

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?

Well-structured with bullet points for modes and warnings. Front-loaded key info. Slightly verbose but each part adds value. Could be marginally shorter but still effective.

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 all aspects: pre-condition (check parameters), post-condition (download URL, local save), mode-specific details, parameter constraints. No output schema, but response description is sufficient. Comprehensive for a complex tool with nested object.

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 description adds critical context: outputDir default behavior, includePreview only when needed, params must come from get_design_parameters, shareType codes mapping. Enhances 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 the tool generates a PDF synchronously with a download URL. It distinguishes from async siblings and download tools, and explains mode-specific behavior (stdio vs HTTP). The purpose is unambiguous.

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

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

Explicitly instructs to call get_design_parameters first, ask user for values, and avoid placeholder/fake data. Also provides when to use includePreview and outputDir. Differentiates from async tools and download 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 provide readOnlyHint and idempotentHint, so the description adds context about what specific information is retrieved (types/structures). No additional behavioral traits 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?

Two concise sentences with front-loaded key information. No extraneous 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 read-only tool with two parameters and comprehensive annotations, the description fully covers necessary context. No output schema needed as return is straightforward.

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

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

Schema coverage is 100% with clear descriptions for both parameters. Description does not add meaning beyond what the schema provides, so baseline of 3 is appropriate.

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

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

Description clearly states the tool retrieves parameter structure of design templates. It specifically uses verb 'get' and resource 'design template parameters', distinguishing it from sibling tools like generate_pdf_* or list_templates.

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?

Implies usage for inspecting parameter structure before form generation, but does not explicitly state when to use or alternatives. No exclusions or when-not-to-use guidance.

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

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

Annotations already declare readOnlyHint and idempotentHint true, indicating safe, idempotent behavior. The description adds value by specifying the exact return fields (ID, name, version, thumbnail URL) and the purpose of the output, which is not covered by 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 extremely concise: two sentences, no filler. First sentence states the core function and output, second sentence provides usage guidance. Perfectly front-loaded and 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 parameters and no output schema, the description fully covers what the tool does, what it returns, and how to use the result. No missing information for an agent to correctly invoke and utilize the 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?

Tool has zero parameters, so schema coverage is 100%. Baseline score of 4 applies as the description does not need to add parameter information.

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 retrieves a list of designs in the workspace and specifies the returned fields (ID, name, version, thumbnail URL). It also explains how to use the IDs with downstream tools, differentiating its purpose from siblings.

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 explains that the obtained ID should be used as designId for PDF generation and get_design_parameters. It provides clear context for when to use the tool, though it does not explicitly list when not to use it or mention 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 declare readOnlyHint=true. The description adds context about client-side AI (Sampling), no server API key needed, and the need for user approval, enhancing 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 a single paragraph that conveys essential information efficiently, though it could be slightly more structured for easier parsing.

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 output purpose. It covers prerequisites (Sampling), workflow (user approval), and usage context, making it fairly complete for a utility 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 covers all parameters with descriptions. The description does not add significant new semantics beyond implying description is natural language, so baseline score applies.

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

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

The description clearly states the tool assembles params JSON for generate_pdf_sync using natural language and designId via Sampling. It distinguishes from sibling tools like generate_pdf_sync and is specific about its role.

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 states it is not usable on clients without Sampling support and instructs to get user approval before passing to generate_pdf_sync, providing clear usage context.

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