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

No annotations are present, so the description carries full burden. It explains the return dictionary structure (e.g., similarity score, unique lines) but does not disclose limitations like handling of scanned PDFs or performance characteristics.

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 somewhat verbose with a full Args/Returns block. While well-structured, it could be more concise without losing 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?

Given the tool's complexity (text comparison), the description covers input parameters and return fields, including similarity. However, it lacks details on edge cases (e.g., missing pages) and has 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 description coverage is 0%, but the description adds meaning by explaining each parameter (e.g., file_path as 'full path', page numbers as 1-based). This compensates 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 tool's purpose: comparing text differences between two PDF pages. It uses a specific verb ('compare') and resource ('PDF pages'), differentiating it from sibling tools like get_pdf_page_info or read_pdf_as_text.

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 versus alternatives is provided. The description only states the general purpose, lacking context or exclusions for 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 bears full responsibility for behavioral disclosure. It explains input/output but omits important traits such as how it handles corrupted PDFs, permissions required, or whether images from headers/footers are included. Edge cases are not addressed.

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 well-structured with clear 'Args' and 'Returns' sections, and each sentence serves a purpose. It is concise enough, though the Returns section could be slightly more compact without losing clarity.

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

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

The description covers input parameters and return values adequately for a tool with 4 params and no output schema. However, it lacks context about error handling, performance implications, or how it compares with siblings. Given the complexity of PDFs, more details on unsupported cases would improve 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?

With 0% schema description coverage, the description adds significant meaning by explaining each parameter's purpose, defaults, and filtering behavior. However, the format for the 'pages' parameter (e.g., '1-5,7') is not specified, leaving some ambiguity. Overall, it partially compensates for the missing 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 extracts embedded images from PDF files, using the verb 'extract' and specifying the resource 'PDF images'. It distinguishes well from sibling tools like 'read_pdf_as_images' (which converts pages to images) and 'extract_pdf_tables' (extracts tables).

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 does not provide explicit guidance on when to use this tool versus alternatives. For instance, it does not mention that for extracting images from the entire page as rendered, 'read_pdf_as_images' should be used instead, nor does it specify prerequisites 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?

No annotations provided, and the description only states it extracts links. It does not disclose non-destructive behavior, performance characteristics, or potential side effects (e.g., file modification).

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 and includes structured Args and Returns sections. However, it is written in Chinese, which may reduce clarity for some agents.

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

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

The description provides return value structure, compensating for no output schema. However, it lacks error handling, prerequisite conditions, or examples, leaving gaps for a moderately complex 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?

The description explains the purpose of both parameters: file_path as the full path and pages as an optional page range. This adds meaning beyond the schema's type definitions.

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

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

The description clearly states the tool extracts all links (URLs and internal jumps) from a PDF, using a specific verb and resource. It distinguishes itself from sibling tools like extract_pdf_tables or extract_pdf_images.

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 versus alternatives (e.g., search_pdf_text, get_pdf_info) or exclusions. No mention of prerequisites 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?

No annotations are provided, so the description carries the full burden. It mentions dependency on PDF structure and a caveat about complex/scanned PDFs, but does not explicitly state that the tool is read-only or discuss permissions, performance, or side effects.

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 a clear header, a useful caveat note, and structured Args/Returns sections. Every sentence adds value without unnecessary verbosity.

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 2 parameters and no output schema, the description adequately explains the return structure in detail. However, it does not cover error handling or the exact format for the pages parameter, leaving some gaps.

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

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

Schema description coverage is 0%, so the description must compensate. It explains both parameters: file_path as the full path and pages as an optional range (default all pages). However, the format of the page range is not specified (e.g., '1-3,5').

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: '提取PDF中的表格数据' (extract tabular data from PDF). It uses a specific verb and resource, and is well distinguished from siblings that extract text, images, links, etc.

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 includes a note about limitations: '表格提取依赖PDF的结构，对于复杂或扫描版PDF可能效果不佳' (table extraction depends on PDF structure; may not work well for complex or scanned PDFs). This provides when-not-to-use guidance, but it does not explicitly mention alternative tools from the sibling list.

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 describes the return format and parameters but does not disclose potential side effects, authorization needs, or rate limits. It is adequate but not rich.

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 and well-structured, using bullet points for arguments and returns. Every sentence adds value without redundancy.

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

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

Given no output schema, the description thoroughly explains the return dictionary structure. Parameter descriptions are sufficient, and the tool fits clearly among PDF siblings. It is complete for the tool's complexity.

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

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

Schema coverage is 0%, so the description must compensate. It explains file_path as full path and pages as optional range with default all pages. This adds meaning beyond the bare schema, meeting the baseline for low coverage.

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 it annotates PDF files (getting 批注、高亮、下划线等). It uses a specific verb and resource, and distinguishes from sibling tools like get_pdf_info or read_pdf_as_text by focusing solely on annotations.

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 annotations but does not explicitly state when to use it versus alternatives, nor does it mention prerequisites or exclusions. It lacks guidance on 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 provided, so the description must cover behavior. It lists return fields but does not state that the operation is read-only, nor does it mention permissions, file existence requirements, or error handling. The implied nature (local file read) provides some 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 well-structured with Args and Returns sections, listing all return fields. It is concise with no unnecessary content, though it could be slightly shorter.

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

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

Given no output schema, the description adequately details the return dictionary. However, it omits edge cases (e.g., missing file, encrypted handling) and does not position itself among the 12 sibling tools, which could confuse selection.

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 single parameter file_path is described as 'PDF文件的完整路径' (full path of PDF file), adding meaning beyond the schema's title 'File Path'. This compensates for 0% schema coverage.

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 it retrieves basic PDF metadata (page_count, title, author, etc.), distinguishing it from siblings like read_pdf_as_text (text content) or get_pdf_page_info (page-specific data). However, it doesn't explicitly contrast with siblings.

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

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

No guidance on when to use this tool versus alternatives such as get_pdf_page_info or extract_pdf_tables. The description lacks context about prerequisites or scenario appropriateness.

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 details return values (has_outline, outline_count, outline with level, title, page) but does not mention error handling, file existence prerequisites, or that it is a read-only operation.

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 a clear purpose line and structured Args/Returns sections. However, it could be more succinct by removing redundant Chinese/English phrasing.

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 simplicity, the description adequately explains the return format. However, it lacks information on error conditions (e.g., invalid file) and performance considerations, which would be expected for a file processing 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 0%, but the description adds the parameter meaning: 'full path of PDF file'. This compensates for the lack of schema descriptions and adds context beyond the parameter 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 verb 'get' and the resource 'PDF bookmark/outline structure', making it distinct from sibling tools like get_pdf_info or read_pdf_as_text.

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 versus alternatives, such as comparing with get_pdf_info for other PDF properties. The description only explains what the tool does, not the context of use.

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. It discloses that the tool returns a dictionary with specific fields but does not mention if it is read-only, requires file permissions, or handles errors. Basic disclosure is present, but more detail on behavioral traits is missing.

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 structured with Args and Returns sections, making it easy to parse. It is not overly concise but is well-organized and front-loaded with the purpose. Could be slightly shortened without losing clarity.

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 simplicity (2 required params, no output schema), the description adequately explains parameters and return values. However, it lacks information on error handling or edge cases (e.g., invalid path or page number).

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 fully explains both parameters: 'file_path: PDF文件的完整路径' and 'page: 页码（从1开始）', adding clear meaning beyond just names and types.

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 '获取PDF指定页面的详细信息' (get details of a specified PDF page), specifying the verb 'get' and the resource 'PDF page info'. It distinguishes this tool from siblings like 'get_pdf_info' (which likely covers the whole document) by focusing on a single page's detailed properties.

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 does not explicitly state when to use this tool versus alternatives. It implies usage for getting detailed page info but lacks guidance on prerequisites, exclusions, or conditions where another sibling would be more 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 relies entirely on its own text. It thoroughly details return values (including 'is_likely_scanned') and implies safe, read-only behavior. However, it omits potential performance impacts or file access requirements.

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 front-loaded with the main purpose and uses a clear Args/Returns structure. It is concise, though the Returns section could be slightly trimmed; overall, 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 relatively simple tool with two parameters and no output schema, the description covers all necessary information: parameter explanations and a detailed list of return fields. It is complete for effective agent 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?

Despite 0% schema coverage, the description fully compensates by defining each parameter: 'file_path' as the full path and 'pages' as an optional page range (default all pages). This adds meaning beyond the schema's minimal titles.

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 function: retrieving PDF text statistics (word count, character count, etc.). It distinguishes itself from siblings like 'read_pdf_as_text' (extraction) and 'get_pdf_info' (metadata) by focusing solely on analytical metrics.

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 does not provide explicit guidance on when to use this tool versus alternatives. It only states what it does, leaving the agent to infer appropriate usage without mentioning exclusions or contexts.

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 fully discloses behavior: images are base64 encoded, return structure includes page number, dimensions, format, and truncation info. It explains the max_total_bytes_mb limit and that quality only applies to jpeg, giving agents full awareness of output characteristics and constraints.

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 well-structured: a concise summary sentence followed by Args and Returns sections. Each sentence adds essential information without redundancy. Despite length, it is efficiently organized and front-loaded with the core purpose, making it easy for an agent to scan.

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 6 parameters and no annotations, the description thoroughly covers all inputs (including edge cases like mixed page formats) and outputs (including truncated and warning fields). The output schema exists, but the description still explains return elements, making the tool fully understandable.

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 0% description coverage, so the description provides all parameter semantics. It explains file_path requirement, pages format (with examples), dpi trade-offs, image_format defaults, quality range and exclusive jpeg applicability, and max_total_bytes_mb. This adds significant value beyond the 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 clearly states the tool converts PDF pages to base64 images, specifies the verb and resource, and explicitly mentions suitable scenarios (retaining layout, charts, formulas), distinguishing it from sibling tools like read_pdf_as_text.

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 (scenarios needing original layout) and includes detailed parameter usage guidance. It does not explicitly exclude cases or name alternatives, but the purpose and sibling list imply when to choose this over text or other extraction 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 speed, low token consumption, limitation to text PDFs, and includes warnings for scanned PDF detection and truncation. The return structure is also described.

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 well-structured with separate sections for purpose, args, and returns. It is front-loaded with the main purpose and limitations. However, it is somewhat lengthy; slight trimming could improve conciseness without losing value.

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

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

Given the tool has 4 parameters and no output schema, the description fully covers the return dictionary, potential warnings, and parameter behavior. It addresses edge cases like scanned PDFs and result truncation, making it complete for the tool's complexity.

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

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

Schema description coverage is 0%, but the description compensates with detailed explanations of pages, max_pages, and max_chars. The pages parameter is especially well-documented with multiple format examples. The file_path parameter is minimally described, but the schema title is clear.

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 extracts text content from PDFs, specifying it is suitable for text PDFs and distinguishing it from read_pdf_as_images for scanned PDFs. The verb 'extract' and resource 'PDF text' are specific, and the sibling differentiation is explicit.

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

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

The description provides explicit guidance: suitable for text PDFs, not for scanned PDFs, and recommends the alternative tool read_pdf_as_images for scanned PDFs. It also explains the pages parameter in detail, helping the agent understand how to use it correctly.

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. It describes the search operation and return values, but does not explicitly state that the tool is read-only (does not modify the PDF), nor does it mention error handling, performance, or limitations. The default for max_results is disclosed, but behavioral traits beyond that are vague.

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 and well-structured with a brief summary followed by clearly labeled Args and Returns sections. Every sentence adds value, no redundant 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?

Given the presence of many sibling tools (e.g., read_pdf_as_text, extract_pdf_tables), this description sufficiently explains the tool's purpose, inputs, and output format. It lacks information on edge cases (e.g., no matches found) but overall provides enough context for an AI agent to use it correctly.

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 0% description coverage, but the tool description provides clear explanations for each parameter (file_path, query, pages, max_results) in the Args section, including optionality and defaults. It also describes the return structure in detail, compensating well for the lack of 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 searches for text in a PDF and returns match positions and context. It uses a specific verb ('search') and resource ('PDF text'), and distinguishes itself from siblings like read_pdf_as_text (which extracts all text) and extract_pdf_tables (which extracts tables).

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 that this tool is for searching text within a PDF, but it does not explicitly state when to use it versus alternatives such as read_pdf_as_text for full text extraction or get_pdf_text_stats for textual statistics. No exclusions or conditional guidance is provided.

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