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

No annotations are present, so the description must disclose behavior. It states that page numbers are 'stamped' and configurable, but does not clarify whether the file is modified in-place or created anew, nor does it mention default output behavior (though some details are in the schema).

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

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

Two sentences capture the tool's purpose and primary options without extraneous text. 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?

Given 6 parameters and no output schema or annotations, the description is adequate but incomplete. It covers the main function but omits behavior details like output handling or error conditions.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reiterates three key parameters (starting number, pages, placement) but adds no new meaning beyond what the schema already 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?

The description clearly uses 'Stamp page numbers onto a PDF' as the verb+resource, and specifies configurable aspects (starting number, pages, placement). It distinguishes this tool from siblings like add_watermark or merge_pdf by naming a specific function.

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

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

No explicit when-to-use or when-not-to-use guidance is provided. The context of sibling tools suggests this is the only page numbering tool, but the description does not clarify when to prefer it over 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?

With no annotations, the description adequately discloses functionality: stamps every page, explains modes, placement, rotation, opacity, and output path behavior. However, it could mention that the original file is not modified unless output_path is specified.

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 with no wasted words. The first sentence states the main purpose, the second gives critical mode-specific guidance. Ideal conciseness.

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 10 parameters, 2 required, and no output schema, the description covers essential usage (mode, required fields, tuning). It lacks error handling or details on default output behavior, but is sufficient for a watermark tool.

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

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

Schema coverage is 80% so baseline is 3. The description adds value by explaining mode-dependent parameters (`text` for text mode, `image_file` for image mode) and summarizing tuning options, going beyond the schema.

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

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

The description clearly states the verb 'Stamp' and the resource 'watermark onto every page of a PDF'. It distinguishes from sibling tools (e.g., add_page_numbers) by focusing on watermarking with modes for text and image.

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

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

The description provides clear context for using the tool (watermarking PDFs) but does not explicitly state when to use vs alternatives or exclude sibling tools like add_page_numbers.

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?

No annotations present, so description must disclose behavior. It mentions output is a .pdf file on disk and returned path, and notes extreme compression may lose quality. But lacks details on overwrite behavior, quality trade-offs, or error handling.

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

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

Two sentences with no filler. Front-loaded with purpose, then specific parameters. 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 tool with 3 parameters and no output schema, the description covers input, options, and output format. Complete enough for correct usage.

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

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

Schema coverage is 100%, yet description adds meaning: explains compression level values and default, details output_path directory vs file behavior, and clarifies 'extreme' may lose quality. Adds 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?

Clearly states 'Reduce the file size of a PDF' and lists compression levels, effectively distinguishing from sibling PDF tools like conversions and splits.

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 guidance on when to use (reduce file size) and explains compression level options. Does not explicitly state when not to use or mention alternatives, but context is clear relative to siblings.

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

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

With no annotations, the description carries full burden. It states extraction to a new PDF (non-destructive) and specifies page syntax. However, it does not disclose if input file remains unchanged, permissions needed, or behavior for invalid page ranges.

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 with no wasted words. The action and page specification example are front-loaded. Every sentence earns its place.

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 3 parameters, full schema coverage, and no output schema, the description covers the main action and page format. However, it omits details about return value or success indication, which would be helpful since there is no output schema.

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 by providing an example for the 'pages' parameter (e.g., '1,3,5-7') and clarifies the purpose of 'output_path' indirectly. This helps an agent beyond raw 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 uses a specific verb (extract) and resource (pages from a PDF) and clearly states the outcome (new PDF). It distinguishes from siblings like split_pdf and merge_pdf by specifying subset extraction from a single PDF into one new PDF.

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

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

The description implies usage for extracting a subset of pages but provides no explicit guidance on when to prefer this tool over siblings like split_pdf or compress_pdf. No when-not-to-use or alternative mention given the large set of sibling tools.

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

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

No annotations are provided, so the description carries full burden. It discloses that rendering is server-side and external assets may not be fetched, which are key behavioral traits beyond what the schema reveals.

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, each providing essential information. No wasted words, and the primary action is stated first.

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

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

With no output schema, the description does not explain the return value, but the tool's output (PDF) is implied. Given the simplicity and context signals, it is mostly complete.

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

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

Schema description coverage is 100%, so the schema already explains both parameters. The description adds context about rendering limitations but does not add new parameter-level meaning.

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 converts an HTML file to PDF, specifies the file extensions (.html or .htm), and its purpose is distinct from sibling tools that manipulate PDFs or convert other formats.

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 context mentions server-side rendering and that external assets may not be fetched, providing important limitation guidance. However, it does not explicitly state when not to use this tool 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?

With no annotations, the description adds some behavioral context: output path behavior (optional, defaults to first input's directory). However, it does not disclose error handling (e.g., invalid files), overwrite behavior, or required permissions.

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, well-structured sentence that front-loads the main purpose and includes key details without redundancy. Every word earns its place.

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

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

For a simple tool with 2 parameters and no output schema, the description covers purpose, input format, ordering, and output behavior. It lacks details on error handling or invalid inputs but is otherwise sufficient.

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

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

Schema coverage is 100%, but the description adds value by explicitly listing supported image formats (.jpg, .jpeg, .png), which are not mentioned in the input_files schema description. This is crucial for correct 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 combines one or more images into a single PDF, one per page, in order. It specifies supported formats (.jpg, .jpeg, .png) and distinguishes from sibling PDF tools like pdf_to_jpg or ocr_pdf.

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

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

The description implies usage for creating PDFs from images but does not provide explicit guidance on when to use this tool versus alternatives (e.g., office_to_pdf, html_to_pdf). No exclusions or when-not-to-use scenarios are mentioned.

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

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

With no annotations, the description discloses key behaviors: order preservation, output as .pdf file on disk, and return of file path. It does not cover edge cases or error handling, but is adequate for a simple tool.

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 with no fluff. First sentence states the core action, second adds output details. Highly 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?

Lacks details on output_path behavior (directory vs file), error handling, or file existence handling. No output schema, so description should cover return value—it does, but incompletely. Moderate completeness.

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

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

Schema coverage is 100% as both parameters have descriptions. The description adds minimal value beyond the schema (only mentions order preservation and output format). Baseline 3 is appropriate.

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

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

The description clearly states the verb (Merge), resource (PDF files), and action (into a single PDF, preserving order). It distinguishes well from sibling tools like split_pdf or compress_pdf.

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

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

The description implies usage for merging multiple PDFs in order but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.

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?

Discloses significant time (>60 seconds) for large/image-heavy PDFs, which is useful. No annotations exist, so description carries full burden. Missing disclosure on whether the tool overwrites the input file or creates a new one, and if it is destructive.

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. First sentence states clear purpose, second adds language details and time warning. No wasted words.

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

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

No output schema, so description should explain return value or result. It says 'make scanned text selectable/searchable' but doesn't specify what the tool returns (e.g., file path, success message). Also lacks error handling hints. Barely adequate for a tool with this 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% with detailed param descriptions. Description adds value by giving language code examples ('eng', 'spa') and noting that large PDFs take >60s, which is not in schema. Adds contextual nuance 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?

Clear verb+resource (Run OCR on a PDF) with explicit benefit (make scanned text selectable/searchable). Distinct from sibling tools like pdf_to_jpg or pdf_to_word.

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?

Implied usage for OCR, but no explicit when-to-use vs alternatives. Mentions language code acceptance but no guidance on when to select which languages or when to avoid 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?

No annotations are provided, and the description does not disclose behavioral traits such as formatting preservation, file location requirements, error handling, or side effects. The description is minimal beyond the conversion action.

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

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

The description is a single, front-loaded sentence with no wasted words. It efficiently states purpose and accepted formats.

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 conversion tool with no output schema, the description covers basic purpose and formats. However, it lacks information about return value, error behavior, and size limits, making it adequate but not comprehensive.

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 both parameter descriptions exist in the schema. The tool description adds the list of accepted formats, which overlaps with the schema description for input_file, and does not provide additional semantic nuance.

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 verb 'Convert' and the resource 'Microsoft Office document to PDF'. It lists all accepted formats, which distinguishes it from sibling tools that handle PDF-to-other conversions.

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

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

The description implies usage when converting Office files to PDF but does not provide explicit when-to-use or when-not-to-use guidance, nor does it reference alternative sibling tools.

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

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

No annotations are provided, so the description carries full responsibility. It honestly discloses limitations ('non-tabular PDFs may produce messy results'), which is a useful behavioral trait. However, it does not detail other aspects like file size limits or expected processing time.

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

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

The description is two sentences long, with the primary action stated first. Every word serves a purpose, and there is no extraneous information. It is highly concise and well-structured.

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

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

No output schema is provided, yet the description does not explain what the tool returns (e.g., a file path or success message). It also omits details like required permissions or error handling. For a conversion tool with two parameters, this is a noticeable gap.

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

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

The schema covers 100% of parameters with descriptions for input_file and output_path. The description adds value by clarifying the tool's best-case use case (tabular data), which is not present in the schema. It compensates adequately for the lack of parameter-level guidance beyond the schema.

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

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

The description explicitly states 'Convert a PDF to a Microsoft Excel .xlsx spreadsheet' with a specific verb and resource. This clearly distinguishes it from sibling tools like pdf_to_word or pdf_to_powerpoint, which convert to different formats.

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 advises that the tool works best on PDFs with clear tabular data and warns that non-tabular PDFs may produce messy results. While it provides clear context for when to use, it does not suggest alternative tools for non-tabular PDFs.

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?

Discloses return format (zip archive) and mode behavior, but lacks details on nondestructive nature, auth requirements, or error handling. Adequate for a straightforward conversion tool without 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 sentences, no fluff. Front-loaded with main purpose; each sentence adds essential information.

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

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

Covers core behavior, parameters, and return format. Without an output schema, the description adequately describes output. No missing critical details for this low-complexity tool.

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

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

Schema coverage is 100%, but description adds minimal extra context beyond the schema (e.g., zip archive output). No detailed parameter constraints or examples provided.

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 action ('Convert a PDF to JPG images') and specifies the two modes ('pages' and 'extract'), which distinguishes it from sibling tools like pdf_to_word or extract_pdf_pages.

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

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

No guidance on when to use this tool over alternatives (e.g., when to use 'extract' mode vs. extract_pdf_pages). No exclusions or context for choosing among siblings.

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

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

The description mentions that each page becomes an editable slide and that conversion quality depends on the source, adding some behavioral context. However, it lacks details on limitations, file size constraints, or error handling.

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

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

The description is concise with two sentences, front-loading the core purpose and adding one key detail. No unnecessary words.

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

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

For a simple conversion tool with two parameters and no output schema, the description covers the core transformation. However, it could mention the output format or when to use alternatives.

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

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

The input schema has 100% description coverage, so parameters are already documented. The description adds no additional meaning to the parameters beyond what the 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?

The description clearly states the tool converts a PDF to a PowerPoint .pptx presentation, which is a specific verb and resource. It is easily distinguishable from sibling tools like pdf_to_word or pdf_to_excel.

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

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

The description provides no guidance on when to use this tool versus its many siblings (e.g., pdf_to_word, pdf_to_excel). There are no prerequisites or context for when this conversion is appropriate.

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

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

With no annotations, the description carries full burden. It discloses that scanned PDFs yield poor results, which is key behavioral information. However, it does not mention other traits like write behavior or file handling, though that is partially covered by the schema.

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

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

Two sentences, zero waste. The essential information is front-loaded, and 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 conversion tool with no output schema and 100% parameter coverage, the description is complete: it states the purpose, caveats, and a suggested alternative. An agent can correctly select and invoke this tool based on this description.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add additional meaning to the parameters beyond what the schema already provides, such as details on input_file or output_path.

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 'Convert a PDF to an editable Microsoft Word .docx document,' which is a specific verb and resource. It clearly distinguishes this tool from siblings like pdf_to_excel or pdf_to_powerpoint by specifying the output format.

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

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

The description gives clear guidance on when to use this tool and when to avoid it: 'Conversion quality depends on the source (scanned PDFs produce poor results; use ocr_pdf first if needed).' This explicitly suggests an alternative workflow and sets expectations.

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?

No annotations are provided, so the description bears the full burden. It mentions the output requires a password but does not disclose whether the original file is modified, what happens to existing metadata, or security implications beyond the schema's secret handling note.

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 convey the essential function without any redundant or extraneous information. Every word earns its place.

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

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

For a simple tool with 3 parameters and no output schema, the description covers the core action. However, it omits details about output path behavior and any error conditions, leaving some gaps for a complete understanding.

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 parameters are well-documented in the schema. The description adds no additional parameter-level meaning, which is acceptable per baseline.

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

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

The description 'Add password protection to a PDF' clearly states a specific verb and resource. It unambiguously distinguishes from sibling tools like 'unlock_pdf' which remove protection, and other PDF operations.

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

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

The description implies usage for securing a PDF but does not explicitly state when to use or avoid it, nor does it mention alternatives like 'unlock_pdf' for removal. No guidance on prerequisites or 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?

No annotations are provided, so the description bears the full burden. While it honestly states the tool 'attempts' to repair, it lacks details on failure behavior, potential side effects (e.g., modification of original), permission requirements, or success guarantees. Minimal behavioral disclosure.

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

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

The description is two sentences long, front-loads the purpose, and contains no superfluous words. Every sentence provides 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 repair tool with no output schema, the description covers the main action and output format. However, it could mention what happens if the repair fails or if the original file is preserved. Slight gaps prevent a perfect score.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description adds no new information beyond what is in the schema (input_file and output_path). According to the rules, baseline is 3.

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 action ('repair'), the resource ('damaged or malformed PDF'), and the output (a .pdf file on disk). It distinguishes from sibling tools like compress or merge, as repair addresses a distinct use case.

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 specifies when to use the tool ('useful for scanned PDFs that fail to open or render correctly'), providing clear context. It does not explicitly mention when not to use it or suggest alternatives, but the sibling list implies other tools for different tasks.

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?

No annotations provided, so description carries full burden. It states rotation direction and default pages but does not disclose whether the original file is modified, if a new file is created, or any permissions required. Acceptable but not thorough.

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-loaded with purpose and examples. No unnecessary words or repetition.

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

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

No output schema and no description of return value or side effects. Does not mention whether output_path is required or defaults. Lacks details on what the tool produces or whether it modifies in place. Incomplete for a tool with 4 parameters.

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

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

Schema description coverage is 100%, so baseline is 3. Description rephrases schema info (e.g., page examples) but adds no new meaning beyond what schema already 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 verb 'rotate', resource 'pages in a PDF', and specifies degrees (90, 180, 270 clockwise). It also mentions page targeting, distinguishing it from sibling tools like split or merge.

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

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

No explicit guidance on when to use this tool vs alternatives (e.g., extract_pdf_pages, split_pdf). The description gives examples of page selection but lacks context for choosing rotate over other operations.

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

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

With no annotations, the description carries the full burden. It discloses the output format (.zip) and the two splitting modes, but misses details like whether the original file is modified, error behavior if no range is specified, or required permissions.

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-load the main purpose and output. No filler words; every sentence is essential.

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

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

Given the complexity (4 params, no output schema, no annotations), the description covers the main use cases and output format. However, it lacks details on error conditions, file existence requirements, and what happens when both 'ranges' and 'fixed_range' are omitted.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value with an example for 'ranges' and clarifies the behavior of 'output_path' for directories vs files, exceeding basic schema descriptions.

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

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

The description clearly states the tool splits a PDF by page ranges or fixed-size chunks and returns a zip. It specifies the resource (PDF) and action (split), but does not explicitly differentiate from the sibling tool 'extract_pdf_pages' which may have similar functionality.

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

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

The description provides context on when to use the tool (for splitting by ranges or chunks) but does not mention when to avoid it or alternatives like extract_pdf_pages. It implies usage but lacks explicit exclusions.

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

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

With no annotations, the description must cover behavioral traits. It states the tool 'removes password protection' and 'produces an unprotected .pdf file on disk,' but omits details like password security handling (though the schema mentions it), error behavior on wrong password, or whether the original file is modified. This is adequate but minimal.

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 short sentences with no unnecessary words. It front-loads the key action and ends with the output behavior. Every sentence contributes meaningful information.

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

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

For a simple tool with 3 parameters and no output schema, the description explains the input requirement and output file. The schema provides detailed parameter descriptions. The description omits potential error conditions or return values, but overall it is complete enough for the tool's simplicity.

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

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

Schema description coverage is 100%, so the description adds no extra parameter meaning beyond what the schema already provides. The baseline score of 3 is appropriate.

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

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

The description explicitly states the action: 'Remove password protection from a PDF.' It clearly distinguishes this tool from siblings like 'protect_pdf' (which adds protection) and other PDF operations. The verb 'remove' and resource 'PDF' are specific.

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 notes the prerequisite 'Requires the correct password,' which implies when to use: when you have the password. It does not explicitly mention when not to use or alternatives, but the context of sibling tools makes the usage clear.

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