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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool adds annotations but doesn't explain what happens (e.g., modifies the PDF file, requires write permissions, potential side effects like file size changes). 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.

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

The description is a single, clear sentence with no wasted words. It's front-loaded and efficiently conveys the core purpose without unnecessary elaboration.

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 (8 required parameters, mutation operation, no annotations, but has output schema), the description is incomplete. It doesn't address parameter meanings, behavioral traits, or usage context, leaving significant gaps despite the output schema potentially covering return values.

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 0%, so the description must compensate by explaining parameters. It mentions 'annotation' but doesn't clarify what annotation_type, x, y, width, height, or content mean in context. The description adds minimal value beyond the schema's property names.

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 an annotation to a PDF' clearly states the action (add) and resource (annotation to PDF), but it's vague about what constitutes an annotation and doesn't differentiate from sibling tools like pdf_add_text or pdf_add_form_field. It's functional but lacks specificity.

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

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

The description provides no guidance on when to use this tool versus alternatives like pdf_add_text or pdf_add_form_field. There's no mention of prerequisites, context, or exclusions, leaving the agent to infer usage from the tool name alone.

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 the full burden of behavioral disclosure. The description only states the basic action without revealing any behavioral traits: it doesn't mention whether this modifies the original PDF or creates a new one, what permissions are needed, whether the operation is reversible, error conditions, or rate limits. For a mutation tool with zero annotation coverage, this is a critical gap.

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, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it immediately understandable. Every word earns its place, though this conciseness comes at the cost of completeness.

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 (9 parameters, mutation operation), absence of annotations, and 0% schema description coverage, the description is incomplete. While an output schema exists (which reduces the need to describe return values), the description doesn't address critical context: behavioral traits, parameter meanings, usage guidelines, or error handling. For a PDF manipulation tool with many parameters, this leaves significant gaps for the agent.

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

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

Schema description coverage is 0%, meaning none of the 9 parameters have descriptions in the schema. The description adds no parameter semantics beyond the tool name—it doesn't explain what 'field_type' accepts, what 'options' array contains, coordinate systems for x/y/width/height, or format expectations for 'pdf_path'. With 9 undocumented parameters, the description fails to compensate for the schema gap.

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 ('Add a form field') and resource ('to a PDF'), providing a specific verb+resource combination. It distinguishes this tool from siblings like pdf_fill_form (which fills existing fields) and pdf_add_annotation (which adds annotations rather than form fields). However, it doesn't explicitly mention what types of form fields can be added or the scope of the operation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing PDF), when not to use it (e.g., for non-form annotations), or direct alternatives among the sibling tools. The agent must infer usage from the tool name and sibling context alone.

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 for behavioral disclosure. 'Add an image to a PDF' implies a mutation operation, but it doesn't specify whether this modifies the original file in-place, creates a new file, requires specific permissions, has side effects, or handles errors. For a tool with 7 required parameters and no annotation coverage, this is critically inadequate.

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

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

The description is a single, clear sentence with zero wasted words. It's perfectly front-loaded and gets straight to the point without unnecessary elaboration. Every word earns its place in communicating the core function.

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 (7 required parameters, mutation operation), complete lack of annotations, and 0% schema description coverage, the description is woefully incomplete. While an output schema exists, the description doesn't address critical behavioral aspects, parameter meanings, or usage context needed for effective tool invocation.

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

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

Schema description coverage is 0%, meaning none of the 7 parameters have descriptions in the schema. The description provides no information about what any parameter means, their formats, units, or constraints. It doesn't even mention that parameters exist, leaving the agent completely in the dark about how to use this tool effectively.

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 'Add' and the resource 'image to a PDF', making the purpose immediately understandable. It distinguishes from siblings like pdf_add_text or pdf_add_annotation by specifying the type of content being added. However, it doesn't specify whether this modifies the original PDF or creates a new one, which prevents a perfect score.

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

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_add_text for text or pdf_add_annotation for annotations, there's no indication of the specific use case for images versus other additions. No prerequisites, constraints, or comparison to similar tools 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?

No annotations are provided, so the description carries full burden. It states the action ('Add text') but doesn't disclose behavioral traits like whether this modifies the original PDF file, creates a new file, requires specific permissions, handles errors, or has rate limits. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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 appropriately sized and front-loaded, with zero waste, making it easy to parse quickly.

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 (7 parameters, mutation operation) and the presence of an output schema (which reduces need to explain return values), the description is incomplete. It lacks parameter details, usage context, and behavioral transparency, but the output schema helps mitigate some gaps. It's minimally adequate but with clear deficiencies.

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 0%, so the description must compensate. It mentions 'at a specified position,' which hints at x and y parameters, but doesn't explain any of the 7 parameters' meanings, formats, or constraints. The description adds minimal value beyond the schema, failing to address the coverage gap.

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 ('Add') and resource ('text to a PDF'), specifying the action and target. It distinguishes from some siblings like pdf_add_annotation or pdf_add_image by focusing on text, but doesn't explicitly differentiate from all similar tools like pdf_replace_text. The purpose is specific but could be more distinctive.

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

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

The description provides no guidance on when to use this tool versus alternatives. With siblings like pdf_replace_text and pdf_add_annotation available, there's no indication of when text addition is preferred over text replacement or annotation addition. No context 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.

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

With no annotations provided, the description carries full burden of behavioral disclosure. It mentions the automatic detection mechanism but doesn't cover important aspects like whether this modifies the original file or creates a new one, error conditions, performance characteristics, or what the output contains. The description is insufficient 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.

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

The description is a single, well-constructed sentence that efficiently communicates the core functionality. 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.

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

Given the tool's moderate complexity (PDF manipulation with automatic detection), no annotations, and an output schema present, the description is minimally adequate. It explains what the tool does but lacks important behavioral context. The output schema reduces the need to describe return values, but more operational details would be helpful.

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 0%, so the schema provides no parameter documentation. The description doesn't mention any parameters or their meanings, failing to compensate for the schema gap. However, with only 3 parameters and an output schema present, the baseline is 3 as the description doesn't add value but the overall context isn't severely lacking.

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 specific action ('automatically crop'), resource ('a PDF page'), and purpose ('to remove blank margins by detecting content boundaries'). It distinguishes from sibling tools like pdf_crop_page by specifying the automatic content boundary detection aspect.

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 removing blank margins from PDF pages, but doesn't explicitly state when to use this vs. the sibling pdf_crop_page tool or other alternatives. No guidance on prerequisites, limitations, or exclusions is provided.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool combines pages but doesn't describe what happens to the original PDF (e.g., if it's modified or a new file is created), permissions needed, error conditions, or output behavior. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence: 'Combine multiple pages from a PDF into a single page with specified layout.' It's front-loaded with the core purpose and has zero wasted words, 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.

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

Given the tool has an output schema (which likely describes the return value), the description doesn't need to explain output details. However, with 4 parameters, 0% schema coverage, and no annotations, the description is incomplete—it lacks behavioral context and parameter guidance. It's minimally adequate but has clear gaps for a mutation 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 description coverage is 0%, so the description must compensate by explaining parameters. It mentions 'specified layout' which hints at the 'layout' parameter but doesn't detail other parameters like 'pdf_path', 'page_numbers', or 'output_path'. With 4 parameters and no schema descriptions, the description adds minimal semantic value beyond what's inferred from the tool name.

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: 'Combine multiple pages from a PDF into a single page with specified layout.' It specifies the verb ('combine'), resource ('pages from a PDF'), and outcome ('single page with specified layout'), making it easy to understand. However, it doesn't explicitly differentiate from sibling tools like pdf_merge_files or pdf_split, which also manipulate PDF pages, so it doesn't reach the highest score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like pdf_merge_files (which merges entire files) or pdf_split (which splits pages), leaving the agent to infer usage context. There's no explicit when/when-not advice or prerequisites, resulting in minimal 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Crop a page in a PDF' implies a mutation operation that modifies the PDF file, but it doesn't specify whether this creates a new file, modifies in-place, requires write permissions, or has side effects like data loss. It also doesn't mention error conditions, performance characteristics, or output behavior. The description is too minimal for a tool that performs file modifications.

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

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

The description is extremely concise at just 5 words ('Crop a page in a PDF.'). It's front-loaded with the core action and resource, with no unnecessary words or sentences. Every word serves a purpose in conveying the basic function.

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 (7 parameters, mutation operation, coordinate-based cropping) and the absence of annotations, the description is insufficiently complete. While an output schema exists (which might describe return values), the description doesn't address critical context like how cropping works, coordinate systems, file handling behavior, or error scenarios. For a PDF manipulation tool with multiple parameters, this minimal description leaves too many questions unanswered.

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 has 7 parameters with 0% description coverage, meaning none have descriptions in the schema. The tool description provides no information about any parameters—it doesn't explain what 'pdf_path', 'page_number', coordinate parameters (x0, y0, x1, y1), or 'coordinate_mode' represent. For a tool with 7 undocumented parameters, the description fails to compensate for the schema's lack of documentation.

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 'Crop a page in a PDF' clearly states the action (crop) and resource (a page in a PDF), making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling 'pdf_auto_crop_page', which appears to serve a similar function but with automated cropping. The description is specific but lacks sibling differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling 'pdf_auto_crop_page' for automated cropping or explain scenarios where manual cropping with coordinates is preferred over automated methods. There's no context about prerequisites, file formats, or limitations.

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 provided, the description carries the full burden of behavioral disclosure. While 'Delete' implies a destructive operation, it doesn't specify whether this permanently removes the page, creates a modified copy, or allows undo operations. There's no mention of file permissions, error conditions, or what happens to page numbering after deletion. For a mutation tool with zero annotation coverage, this is insufficient.

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

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

The description is perfectly concise at just 6 words. Every word earns its place: 'Delete' specifies the action, 'a page' identifies the target, 'from a PDF' provides context. There's no redundancy or unnecessary elaboration. The structure is front-loaded with the core action immediately apparent.

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 destructive operation with 2 parameters and no annotations, the description is incomplete. While an output schema exists (which reduces the need to describe return values), the description doesn't address critical behavioral aspects like whether the original file is modified, what permissions are required, or how errors are handled. Given the complexity of file manipulation and the presence of many sibling tools, more context is needed.

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

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

The description mentions 'a page' which aligns with the page_number parameter, and 'from a PDF' which aligns with pdf_path. However, with 0% schema description coverage, the description doesn't add meaningful context beyond what's obvious from parameter names. It doesn't explain what format pdf_path expects (file path, URL, etc.) or whether page_number is 0-indexed or 1-indexed. The baseline is 3 since the description minimally acknowledges the parameters.

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

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

The description clearly states the action ('Delete') and resource ('a page from a PDF'), making the purpose immediately understandable. It distinguishes itself from siblings like pdf_merge_files or pdf_split by focusing on page removal rather than file manipulation. However, it doesn't specify whether this modifies the original file or creates a new one, which would have made it a perfect 5.

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

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

The description provides no guidance on when to use this tool versus alternatives. With siblings like pdf_crop_page, pdf_rotate_page, and pdf_auto_crop_page that also modify individual pages, there's no indication of when deletion is preferable to other page-level operations. The description offers no context about prerequisites or typical use cases.

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

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. 'Extract' implies a read operation that doesn't modify the PDF, but it doesn't specify whether images are saved to disk, returned as data, require specific permissions, or have rate limits. For a tool with 2 parameters and no annotation coverage, this is inadequate.

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, efficient sentence with zero wasted words—it directly states the tool's function without unnecessary elaboration. It's appropriately sized and front-loaded, making it easy to parse quickly.

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 has an output schema (which should cover return values), 2 parameters with 0% schema coverage, and no annotations, the description is minimally complete. It states what the tool does but lacks details on behavior, parameters, and usage context, making it adequate only with support from the 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 description coverage is 0%, so the description must compensate, but it adds no parameter information beyond what's implied by the tool name. It doesn't explain what pdf_path expects (e.g., file path, URL), what output_dir does (e.g., directory for saving images, null for in-memory), or format details. Baseline 3 is given due to low coverage, but minimal value is added.

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 ('Extract') and resource ('all images from a PDF'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like pdf_add_image or pdf_get_info, which also involve PDF images in different ways, so it doesn't reach the highest clarity level.

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

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

The description provides no guidance on when to use this tool versus alternatives. With siblings like pdf_add_image (for adding images) and pdf_get_info (which might include image metadata), there's no indication of when extraction is appropriate versus other operations, leaving usage context unclear.

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 the full burden of behavioral disclosure. It states the action ('fill form fields') but lacks critical details: whether this modifies the original PDF or creates a new file, what permissions or formats are required, how errors are handled (e.g., invalid fields), or if there are rate limits. For a mutation tool with zero annotation coverage, this is inadequate.

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, efficient sentence with zero waste—it directly states the tool's action without unnecessary words. It's appropriately sized for a simple tool and front-loaded with the core purpose.

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

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

Given the tool's moderate complexity (2 parameters with nested objects, no annotations, but an output schema exists), the description is minimally complete. The output schema likely covers return values, reducing the need for output details in the description. However, for a mutation tool, it lacks behavioral context and parameter guidance, making it only adequate.

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 0%, so the description must compensate for undocumented parameters. It mentions 'form fields' and 'values', which loosely map to the parameters (pdf_path and field_values), but doesn't explain what pdf_path expects (e.g., file path, URL, or format) or how field_values should be structured (e.g., key-value pairs matching field names). This adds minimal semantic value beyond the schema.

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

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

The description clearly states the verb ('fill') and resource ('form fields in a PDF') with the action ('with values'), making the purpose specific and understandable. However, it doesn't explicitly distinguish this tool from similar siblings like pdf_add_form_field or pdf_replace_text, which prevents a perfect score.

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

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 a PDF with existing form fields), exclusions, or comparisons to siblings like pdf_add_form_field (which might create new fields) or pdf_replace_text (which might handle non-form text).

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 the full burden of behavioral disclosure. It states 'Get metadata and information' but doesn't specify what information is included (e.g., page count, author, creation date), whether it's read-only (implied but not explicit), or any error handling. This leaves significant gaps for a tool with potential complexity.

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, efficient sentence with no wasted words, making it easy to parse. It's appropriately sized for a simple-sounding tool and front-loads the key action and resource.

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 apparent simplicity (1 parameter, no annotations, but has an output schema), the description is minimally adequate. The output schema likely covers return values, reducing the need for description detail, but the lack of parameter semantics and behavioral context leaves it incomplete for reliable use.

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 1 parameter (pdf_path) with 0% description coverage, and the tool description adds no semantic details about it. It doesn't explain what pdf_path represents (e.g., file path, URL, identifier) or its format, failing to compensate for the schema's lack of documentation.

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 'Get' and the resource 'metadata and information about a PDF', making the purpose understandable. However, it doesn't distinguish this read operation from its many siblings (e.g., pdf_set_metadata for writing metadata or pdf_extract_images for extracting content), which prevents a perfect score.

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

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_set_metadata (for writing metadata) and pdf_extract_images (for extracting content), it's unclear if this tool is for basic metadata retrieval, comprehensive info, or something else, leaving the agent without usage 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 carries the full burden of behavioral disclosure. It states the action ('merge') but doesn't cover critical aspects like whether the operation is read-only or destructive, what happens to source files, error handling for invalid inputs, or performance considerations. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence that front-loads the core action ('merge multiple PDF files') and outcome ('into one combined PDF') with zero wasted words. It's appropriately sized for a straightforward tool, 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.

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

Given the tool's moderate complexity (merging files), lack of annotations, and presence of an output schema (which reduces the need to describe return values), the description is incomplete. It covers the basic purpose but misses usage guidelines, behavioral details, and parameter semantics, leaving gaps that could hinder correct tool invocation by an agent.

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

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

Schema description coverage is 0%, so the description must compensate, but it only implies the existence of parameters without detailing them. It mentions 'multiple PDF files' (hinting at 'pdf_paths') and 'one combined PDF' (hinting at 'output_path'), but doesn't explain parameter formats, constraints, or defaults. This adds minimal value beyond the schema, meeting the baseline for partial compensation.

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') and resource ('multiple PDF files') with the outcome ('into one combined PDF'), making the purpose immediately understandable. However, it doesn't distinguish this tool from sibling tools like 'pdf_combine_pages_to_single' or 'pdf_split', which also manipulate PDF files in related ways, so it doesn't reach the highest clarity level.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'pdf_combine_pages_to_single' for combining pages or 'pdf_split' for splitting, nor does it specify prerequisites such as file accessibility or format requirements. This leaves the agent with minimal context for tool selection.

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 provided, the description carries full burden but offers minimal behavioral insight. It states the action ('replace text') but doesn't disclose critical traits like whether the replacement is case-sensitive, if it affects all pages or just specified ones, what happens if old_text isn't found, or if the operation modifies the original file or creates a new one. This leaves significant gaps for safe and effective use.

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

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

The description is extremely concise with a single sentence that directly states the tool's function. There is no wasted language or unnecessary elaboration, making it front-loaded and easy to parse quickly. Every word earns its place by conveying the core action.

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

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

Given the complexity of a PDF text replacement operation (which involves file handling and content modification), no annotations, and 0% schema coverage, the description is inadequate. While an output schema exists (which might cover return values), the description lacks essential context about behavior, parameters, and usage scenarios needed for an agent to invoke this tool correctly and safely.

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 0%, so the description must compensate but fails to do so. It mentions no parameters at all, leaving all 4 parameters (pdf_path, old_text, new_text, page_number) undocumented in terms of meaning, format, or constraints. For example, it doesn't clarify if pdf_path is a local file path or URL, or if page_number is optional for whole-document replacement.

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 ('replace') and resource ('text in a PDF document'), making the purpose immediately understandable. It distinguishes from siblings like pdf_add_text (which adds new text) or pdf_set_metadata (which modifies metadata rather than content). However, it doesn't specify whether this replaces all occurrences or just the first, which keeps it from a perfect score.

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

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 an existing PDF), when not to use it (e.g., for adding text rather than replacing), or sibling tools that might be better for related tasks like pdf_add_text for adding new content or pdf_fill_form for form-based modifications.

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 provided, the description carries full burden but offers minimal behavioral insight. It implies a mutation (rotating pages) but doesn't disclose whether this modifies the original file or creates a copy, what permissions are needed, error conditions, or output format. This leaves significant gaps for a tool that alters PDF content.

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, direct sentence with zero wasted words. It's front-loaded with the core action and resource, making it highly efficient and easy to parse.

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

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

Given the tool's complexity (mutating PDF pages), lack of annotations, and 0% schema coverage, the description is inadequate. While an output schema exists, the description doesn't address critical context like file handling, rotation units, or error scenarios, leaving the agent poorly informed.

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 0%, so parameters are undocumented in the schema. The description adds no semantic information about pdf_path (e.g., file path format), page_number (e.g., 1-indexed), or rotation (e.g., degrees, direction). It fails to compensate for the schema's lack of documentation.

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 ('Rotate') and resource ('a page in a PDF'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like pdf_crop_page or pdf_auto_crop_page, which also modify page geometry, so it doesn't reach the highest score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing PDF), exclusions, or comparisons to similar tools like pdf_crop_page for different page adjustments.

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 provided, the description carries the full burden of behavioral disclosure. It states the tool sets metadata but fails to describe critical traits such as whether it modifies the PDF in-place or creates a new file, what permissions are required, or potential side effects (e.g., overwriting existing metadata). This leaves significant gaps in understanding the tool's 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?

The description is a single, efficient sentence with no wasted words, making it easy to parse. It is appropriately sized for a simple tool, though this brevity contributes to gaps in other dimensions like guidelines and transparency.

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 (2 parameters with nested objects, no annotations, and an output schema exists), the description is incomplete. It does not explain what metadata can be set, how the tool behaves, or reference the output schema for results. For a mutation tool with rich input structure, 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.

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

Schema description coverage is 0%, so the description must compensate but does not. It mentions 'metadata' generically without explaining what keys or values are supported (e.g., strings for title, author). The input schema shows 'pdf_path' and 'metadata' as required objects, but the description adds no meaning beyond the schema's structure, failing to clarify 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 'Set metadata for a PDF' clearly states the action (set) and resource (PDF metadata), making the purpose understandable. However, it lacks specificity about what metadata can be set (e.g., title, author, keywords) and does not distinguish it from sibling tools like 'pdf_get_info' which might retrieve metadata, leaving room for ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites (e.g., needing an existing PDF file), exclusions, or how it differs from siblings like 'pdf_get_info' or other PDF manipulation tools, leaving the agent without context for tool selection.

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 states the action ('split') but doesn't disclose behavioral traits like whether it modifies the original file, creates new files, requires specific permissions, handles errors, or has performance considerations. For a tool that presumably creates output files, this lack of transparency about file handling and side effects is inadequate.

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, efficient sentence that front-loads the core purpose. Every word earns its place with no redundancy or fluff. It's appropriately sized for a straightforward tool.

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

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

Given the tool's moderate complexity (splitting PDFs with 3 parameters) and the presence of an output schema (which likely describes the return values), the description is minimally adequate. However, with no annotations and 0% schema description coverage, it should provide more context about file operations, error handling, or usage scenarios to be truly 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 0%, so the description must compensate. It mentions 'individual pages or page ranges', which relates to the 'page_ranges' parameter, but doesn't explain 'pdf_path' or 'output_dir'. The description adds minimal meaning beyond the schema's parameter names, failing to fully compensate for the coverage gap. With 3 parameters and no schema descriptions, baseline expectations are higher.

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 ('split') and resource ('a PDF'), specifying it can be done 'into individual pages or page ranges'. It distinguishes from siblings like pdf_merge_files or pdf_delete_page by focusing on splitting rather than merging, deleting, or other operations. However, it doesn't explicitly differentiate from all siblings (e.g., pdf_combine_pages_to_single might be related but opposite).

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, when splitting is appropriate versus other PDF operations, or any context for choosing between individual pages or page ranges. With many sibling tools available, this lack of differentiation is a significant gap.

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