Server Quality Checklist

Tool Scores

• pdf_add_watermarkC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries full burden but lacks behavioral details. It states the tool modifies PDFs (implied mutation) but doesn't disclose if it's destructive to the original file, requires specific permissions, has rate limits, or what happens on failure. This is a significant gap for a tool that alters files.

  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 purpose ('Add a text watermark to all or specific pages of a PDF'). It wastes no words and is appropriately sized for the tool's complexity.

  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 no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., success status, error messages), behavioral traits like file handling, or usage context, leaving gaps that could hinder an AI agent's correct 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 parameters are well-documented in the schema. The description adds minimal value beyond implying 'pages' parameter usage for targeting, but doesn't provide additional context like format examples or constraints beyond what the schema already covers.

  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 ('Add a text watermark') and resource ('to a PDF'), specifying it can target 'all or specific pages'. It distinguishes from sibling tools like pdf_rotate or pdf_merge by focusing on watermarking, though it doesn't explicitly contrast with them.

  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. While the description implies it's for adding watermarks, it doesn't mention prerequisites (e.g., file permissions), when not to use it, or how it compares to similar tools like pdf_set_metadata for document marking.

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

• pdf_createC
  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 full burden for behavioral disclosure. It states the tool creates a PDF but doesn't mention side effects (e.g., file system writes), permissions needed, error conditions, or output format. For a tool that writes files, this lack of transparency about its behavior and potential impacts is a significant gap.

  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, clear sentence that efficiently conveys the core function without unnecessary words. It's front-loaded with the main action and resource, making it easy to parse. Every word earns its place, and there's no redundancy or fluff.

  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 tool has 4 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., success status, file path), error handling, or behavioral details like file overwriting. For a creation tool with moderate complexity, more context is needed to guide effective 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%, so the schema fully documents all parameters (output, text, title, fontSize). The description adds no parameter-specific information beyond implying 'text' is the content source. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, though the description doesn't enhance understanding of parameter roles 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 action ('Create') and resource ('PDF document from plain text content'), making the purpose immediately understandable. It distinguishes from siblings like pdf_merge or pdf_extract_text by focusing on creation from text rather than manipulation or extraction. However, it doesn't explicitly contrast with all siblings (e.g., pdf_set_metadata could also involve document creation aspects).

  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 prerequisites (e.g., needing text content), when not to use it (e.g., for adding watermarks or merging existing PDFs), or refer to sibling tools like pdf_merge for combining documents. The agent must infer usage from the name and description alone.

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

• pdf_delete_pagesC
  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 action ('Delete') but lacks critical details: whether the operation is destructive (modifies the original file or creates a new one), permissions required, error handling for invalid pages, or output format. This is inadequate for a mutation tool with zero annotation coverage.

  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 directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it highly concise and well-structured for quick understanding.

  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 a destructive PDF operation, no annotations, and no output schema, the description is insufficient. It doesn't cover behavioral aspects like side effects, error conditions, or what the output contains, leaving significant gaps for an AI agent to use the tool correctly in context.

  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 all three parameters (file path, output path, page numbers). The description adds no additional meaning beyond what the schema provides, such as explaining page numbering conventions or file format constraints, so it meets the baseline for high schema coverage.

  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 ('Delete') and resource ('specific pages from a PDF'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like pdf_extract_pages or pdf_split, which also manipulate PDF pages, so it misses the highest score for sibling distinction.

  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 siblings like pdf_extract_pages (extracts pages) and pdf_split (splits PDFs), there's no indication of scenarios where deletion is preferred over extraction or how it differs from other page-manipulation tools.

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

• pdf_extract_textC
  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 extracts text but doesn't describe how it handles errors (e.g., invalid files, unsupported PDFs), performance traits (e.g., speed, memory usage), or output format (e.g., plain text, structured data). For a tool with no annotations, this leaves significant gaps in understanding its behavior beyond the basic function.

  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 and front-loaded: the first sentence states the core purpose, and the second adds optional functionality. There is no wasted language or redundancy, making it efficient and easy to parse quickly.

  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 PDF text extraction (which can involve encoding issues, layout preservation, etc.), no annotations, and no output schema, the description is incomplete. It doesn't explain what the extracted text looks like (e.g., raw text, with formatting markers), potential limitations, or error handling. For a tool with 3 parameters and no structured output information, more context is needed to use it effectively.

  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 description adds minimal value beyond the input schema, which has 100% coverage. It mentions 'optionally specify page range,' aligning with the startPage and endPage parameters in the schema. However, it doesn't provide additional context like format details or usage examples. With high schema coverage, the baseline is 3, as the schema already documents parameters thoroughly.

  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: 'Extract text content from a PDF file.' It specifies the verb ('extract') and resource ('text content from a PDF file'), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like pdf_extract_pages or pdf_info, which might also involve text extraction or provide text-related information.

  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 minimal guidance: 'Optionally specify page range.' It implies usage for text extraction but offers no explicit advice on when to use this tool versus alternatives like pdf_extract_pages (which might extract pages as files) or pdf_info (which could provide metadata including text summaries). There are no exclusions, prerequisites, or comparisons to sibling tools mentioned.

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

• pdf_mergeC
  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. It states the action ('merge') but lacks behavioral details such as whether it overwrites existing output files, handles errors (e.g., invalid PDFs), requires specific permissions, or has performance constraints. This leaves significant gaps for an agent to understand operational risks.

  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 directly states the tool's function without unnecessary words. It's front-loaded and wastes no space, making it easy for an agent to parse quickly.

  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 merging files (a mutation operation) with no annotations and no output schema, the description is insufficient. It doesn't cover error handling, output format details, or side effects, leaving the agent with incomplete information to use the tool safely and effectively.

  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 parameter descriptions in the schema itself (e.g., 'Array of PDF file paths to merge (in order)'). The description adds no additional semantic context beyond what the schema provides, so it meets the baseline for high coverage without extra value.

  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 ('merge') and resource ('multiple PDF files into a single PDF'), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like pdf_reorder or pdf_create, which might involve similar PDF manipulation but serve distinct purposes.

  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 prerequisites (e.g., file accessibility), exclusions (e.g., not for merging non-PDFs), or comparisons to siblings like pdf_reorder (which might reorder pages without merging files).

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

• pdf_set_metadataC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries full burden but provides minimal behavioral context. It states the operation ('Set or update') but doesn't disclose whether this modifies the original file (vs. creating a new one), what happens if metadata fields are omitted, permission requirements, error conditions, or output format. The mention of 'output' parameter in schema hints at file creation, but this isn't explained in the description.

  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 with zero wasted words. It front-loads the core purpose ('Set or update PDF metadata') and succinctly lists the fields without unnecessary elaboration, making it easy to parse quickly.

  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, no annotations, and no output schema, the description is incomplete. It lacks critical context such as whether the operation overwrites the original file, how partial updates work, what the output contains (e.g., success confirmation or error details), and any side effects or limitations. The high parameter count and mutation nature demand more disclosure than provided.

  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 parameters are well-documented in the schema. The description adds marginal value by listing the metadata fields (title, author, subject, keywords, creator) that map to some parameters, but doesn't explain interactions (e.g., that 'file' and 'output' are required while others are optional for partial updates) or provide usage examples beyond what the schema already specifies.

  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 ('Set or update') and resource ('PDF metadata') with specific fields listed (title, author, subject, keywords, creator). It distinguishes from siblings like pdf_info (which reads metadata) and pdf_create/merge/split (which create/transform PDFs), though it doesn't explicitly name alternatives.

  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 on when to use this tool versus alternatives is provided. While the description implies it's for modifying metadata, it doesn't specify prerequisites (e.g., needing an existing PDF file), exclusions (e.g., not for creating new PDFs), or direct comparisons to siblings like pdf_info for reading metadata.

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

• pdf_extract_pagesB
  3.2/5.0
  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 mentions creating a new PDF file but lacks critical behavioral details: whether the source file is modified, what happens if page ranges are invalid, if authentication or permissions are needed, or any rate limits. This is inadequate 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 a single, efficient sentence that front-loads the core action and outcome. Every word earns its place with no redundancy or unnecessary details, making it highly concise and well-structured.

  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 tool's complexity (mutation with 4 required parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain behavioral traits, error conditions, or return values, leaving significant gaps for an AI agent to understand and invoke 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%, so the schema fully documents all 4 parameters. The description adds no additional parameter semantics beyond implying page extraction, which the schema already covers with startPage and endPage descriptions. Baseline 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.

  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 ('extract a range of pages'), the resource ('from a PDF'), and the outcome ('into a new PDF file'). It distinguishes from siblings like pdf_extract_text (extracts text) and pdf_delete_pages (removes pages), making the purpose unambiguous.

  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 sibling tools like pdf_split (which might handle page extraction differently) or clarify scenarios where this is preferred over other PDF manipulation tools, leaving usage context implied.

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

• pdf_reorderB
  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 but lacks behavioral details. It doesn't mention whether the operation modifies the original file, creates a new file, requires specific permissions, or handles errors. 'Reorder pages' implies mutation but lacks transparency about the actual behavior.

  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 perfectly concise with two clear sentences that directly state the tool's purpose and the key parameter requirement. 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.

  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 no annotations and no output schema, the description is incomplete. It doesn't explain what happens to the original file, what the output contains, or potential side effects. Given the complexity of file manipulation, more context is needed.

  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 parameters thoroughly. The description adds minimal value by hinting at the 'order' parameter's purpose but doesn't provide additional semantics beyond what's in the schema descriptions.

  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 ('reorder pages') and resource ('PDF'), distinguishing it from siblings like pdf_merge (combines files) or pdf_delete_pages (removes pages). It directly answers what the tool does with no ambiguity.

  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 like pdf_merge (for combining pages from multiple files) or pdf_extract_pages (for selecting specific pages). The description only states what it does, not when it's appropriate.

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

• pdf_rotateB
  3.2/5.0
  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 mentions the rotation action but fails to disclose critical behavioral traits: whether it modifies the original file (likely not, given output parameter), requires specific permissions, handles errors (e.g., invalid file paths), or has side effects like creating new files. This is inadequate for a mutation tool with zero annotation coverage.

  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 with zero waste. It front-loads the core action ('rotate pages of a PDF') and specifies the angles without unnecessary elaboration, making it easy to parse and understand quickly.

  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 tool's complexity (mutation with 4 parameters) and lack of annotations or output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., success status, error messages) or behavioral nuances like file overwriting. For a PDF manipulation tool among many siblings, more context is needed to guide proper 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%, so the schema fully documents all parameters (file, output, angle, pages). The description adds no additional meaning beyond what's in the schema, such as explaining angle units or page numbering conventions. Baseline 3 is appropriate when the schema does all the work.

  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 verb 'rotate' and the resource 'pages of a PDF', specifying the exact rotation angles (90, 180, or 270 degrees). It distinguishes from siblings like pdf_reorder (rearranges pages) or pdf_extract_pages (removes pages), making the purpose specific and unambiguous.

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

  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 like pdf_reorder for page arrangement or pdf_extract_pages for removal. It lacks context about prerequisites (e.g., file must exist) or exclusions, leaving the agent to infer usage from the name alone.

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

• pdf_infoB
  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 the full burden of behavioral disclosure. While 'Get PDF metadata' implies a read-only operation, it doesn't explicitly state this, nor does it address potential errors (e.g., invalid file paths, corrupted PDFs), performance characteristics, or output format. The description lacks details on what happens if metadata fields are missing or how dates are formatted.

  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 purpose ('Get PDF metadata') and immediately lists the specific data retrieved. Every word earns its place with zero redundancy, making it easy to parse quickly.

  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, read-only operation) and 100% schema coverage, the description is minimally adequate. However, without annotations or an output schema, it fails to fully compensate by not explaining the return format (e.g., structured object vs. text), error handling, or edge cases like missing metadata fields.

  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 the single parameter 'file' clearly documented as 'Path to the PDF file'. The description adds no additional parameter semantics beyond what the schema provides, such as file format requirements or path resolution rules. With high schema coverage, the baseline score of 3 is appropriate.

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

  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 ('Get PDF metadata') and enumerates the exact resources retrieved (page count, title, author, creator, creation date, file size). It distinguishes itself from sibling tools like pdf_extract_text or pdf_set_metadata by focusing on metadata extraction rather than content manipulation or modification.

  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 prerequisites (e.g., file must exist), exclusions (e.g., encrypted PDFs), or comparisons to sibling tools like pdf_set_metadata for setting metadata or pdf_extract_text for content extraction.

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

• pdf_splitA
  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. It mentions the tool's actions (splitting/extracting) but lacks details on behavioral traits like whether it modifies the original file, handles errors, requires specific permissions, or produces output files with specific naming conventions. This is a significant gap 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 two concise sentences with zero waste, front-loading the core purpose. Every word earns its place, making it easy to scan and understand quickly.

  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 is adequate for a basic understanding but incomplete for a mutation tool. It covers what the tool does but lacks details on behavior, error handling, or output specifics, leaving gaps in contextual understanding.

  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 parameters. The description adds minimal value by implying the 'pages' parameter is optional and that omission triggers individual page splitting, but this is also hinted in the schema. Baseline 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.

  Purpose5/5

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

  The description clearly states the tool's purpose with specific verbs ('split', 'extract') and resource ('PDF'), and distinguishes it from siblings like pdf_merge (combines) or pdf_delete_pages (removes). It explicitly mentions two modes: extracting specific pages or splitting into individual pages.

  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 when to use this tool (to split PDFs into separate files or extract pages) but doesn't explicitly compare it to alternatives like pdf_extract_pages (which might overlap in functionality) or provide guidance on when not to use it. No prerequisites or exclusions are mentioned.

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