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

With no annotations, the description discloses return information (status, address, path). It could mention idempotency or non-destructiveness, but the provided context is adequate for a read-only check.

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 purpose, usage guidance, and return info in separate sections. It is concise, though the '节省 token 场景' line could be integrated more tightly.

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

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

Given no parameters and an output schema, the description covers the key return fields in plain language. It lacks details on error handling or potential network issues 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?

No parameters exist, so the description naturally adds no parameter info. Schema coverage is 100%, meeting the baseline and earning a high score.

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 checks the Umi-OCR service status, with a specific verb ('检查') and resource ('Umi-OCR 服务'). It distinguishes from siblings like 'quick_ocr_status' by providing context for usage before OCR tasks.

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

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

Explicitly advises using this tool before important OCR tasks to confirm service availability and avoid token waste, providing clear when-to-use 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. It discloses key behaviors: automatic paragraph merging, confidence filtering, token saving, and handwriting model switching. This provides sufficient transparency for a read-only tool without destructive 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 (three lines for purpose, two for bullet features, two for params) with clear structure and no redundant text. Every sentence adds value, making it easy for an AI 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 simplicity (2 parameters, output schema present), the description covers the core functionality and parameter guidance. It lacks return format details, but the output schema fills that gap. Overall, it is sufficiently complete for standard 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 schema has 0% description coverage, so the description must compensate. It meaningfully explains both parameters: file_path as 'absolute local path' and is_handwritten as 'switch handwriting model', adding context beyond the schema fields. This is adequate for the two 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 tool extracts text from local images using Umi-OCR v2.1.5, with specific features like paragraph merging and confidence filtering. It distinguishes from sibling tools (e.g., ocr_batch, ocr_directory) that handle different inputs or batch processing, making the purpose unambiguous.

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

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

The description specifies the tool is optimized for AI reading and automatically processes paragraphs, implying its use for single-image text extraction with built-in preprocessing. However, it does not explicitly state when not to use it or suggest alternatives, though sibling names provide implicit 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. It discloses that results are returned in input order and separated by delimiters, which is helpful. However, it does not mention error handling for individual image failures, size limits, or timeouts, leaving gaps for a mutation-like batch 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 and well-structured: a one-line purpose, a usage note, parameter descriptions, and return format. Every sentence adds value with no fluff, achieving high information density.

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 parameters, no annotations), the description covers purpose, usage, parameters, and return format. It lacks details on error handling, prerequisites (e.g., file existence), and limits, but the presence of an output schema mitigates the need to explain return values. Overall, sufficient for typical 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 coverage is 0%, so the description must compensate. It provides clear descriptions for both parameters: 'file_paths: absolute local path list' and 'is_handwritten: whether handwritten notes, default False'. This adds meaningful context beyond the schema's type and title, fully covering parameter semantics.

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 'Batch OCR multiple local images, one call returns all results', which clearly defines the action (batch OCR) and the resource (local images). It distinguishes this tool from siblings that handle single images, PDF pages, or directories, making the purpose unambiguous.

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

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

The description provides a clear use case: 'Save token scenario: When needing to OCR multiple images, avoid multiple MCP call round-trips by merging into one call.' This guides when to use the tool. However, it does not explicitly exclude cases where seperate calls might be better (e.g., incremental results), which keeps it from a perfect score.

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 partially covers behavior: it mentions sorting by filename, compact format, and parameter defaults. However, it does not disclose side effects (e.g., file modification), error handling, or performance characteristics for large directories.

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: a one-line summary, a brief use-case note, and a clean parameter list. Every sentence adds value, no redundant 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?

Given 5 parameters, 1 required, and an output schema, the description covers purpose, parameters, and return format (sorted, compact). It lacks details on permissions, file size limits, or error scenarios, but is adequate for a typical 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 coverage is 0%, but the description fully explains all 5 parameters: directory_path, extensions with default, recursive, is_handwritten (handwritten notes), and confidence_threshold. This adds clear meaning beyond the schema's type/default fields.

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 and resource: '批量 OCR 目录下所有图片' (batch OCR all images in a directory). It highlights the one-step nature (directory scan + batch OCR) and distinguishes from siblings like ocr_batch and ocr_image_base64 by focusing on directory-level input.

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 suggests a use case: saving tokens by avoiding separate directory listing, and indicates suitability for batch extraction from scanned books. However, it does not explicitly compare with sibling tools or state when not to 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?

No annotations are provided, so the description carries full burden. It mentions input format and parameter defaults but omits output format, error handling, rate limits, or size constraints. The output schema exists but the description does not reference return values.

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 structure: purpose, use case, parameter list. Each sentence adds value, though the token-saving scenario could be inferred. No unnecessary 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?

Given the tool's simplicity (2 params, no nesting) and existence of an output schema, the description is adequate but incomplete. It lacks mention of return values or error scenarios, requiring the agent to rely on 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%, but the description adds meaning: image_base64 clarifies prefix allowance ('含或不含 data URL 前缀均可') and is_handwritten explains default false. This compensates for the schema's lack of 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 states 'Extract text directly from base64 encoded images', clearly specifying the verb and resource. It distinguishes from sibling tools (e.g., ocr_directory, ocr_pdf_page) by implying base64 input, but does not explicitly compare alternatives.

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

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

The description explains a token-saving scenario when base64 is already available ('当图片已经以 base64 形式存在...省去写入文件步骤'). This provides usage context but lacks explicit when-not-to-use or comparison with 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?

No annotations provided, so description carries full burden. Describes core behavior, parameters affecting output (e.g., is_handwritten, confidence_threshold), and return type (text or error). Lacks mention of limitations like file size or language support, but sufficient for basic usage.

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

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

Well-structured with a concise purpose statement, usage scenario, parameter list, and return info. Every sentence adds value; no 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 5 parameters (1 required), no annotations, and expected output, the description fully covers parameter semantics, usage context, and return values. No obvious gaps for a tool of 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 description coverage is 0%, but description thoroughly explains each parameter: pdf_path, page_number, is_handwritten, dpi, and confidence_threshold, including defaults and rationale for dpi as a balance between accuracy and speed. Adds significant 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 the tool's function: OCR extraction of text from a specified PDF page. Distinguishes from sibling tools by emphasizing direct PDF page OCR versus other OCR methods like image-based or batch processing.

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

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

Provides explicit scenarios where the tool is beneficial (saving tokens by bypassing multi-step workflow, especially for exam PDFs and scanned textbooks). Does not specify when not to use, but context is clear.

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 burden of behavioral disclosure. It states the return values (running/stopped/error) and the performance trade-off (saves tokens). However, it does not specify what causes errors, permissions required, or side effects, but for a simple read-only status check, this is sufficient.

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: two sentences and a return type list. Core information is front-loaded, and every sentence adds value. No wasted text.

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

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

Given no parameters and a simple output, the description fully covers the tool's purpose, output format, and usage trade-offs. It references a sibling tool for context and mentions error cases. Output schema existence is noted, but description independently explains the return type.

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?

There are zero parameters, so the schema coverage is 100%. The description adds no parameter details, but none are needed. Baseline of 4 is appropriate.

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

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

Description clearly states the tool checks OCR service status and returns either 'running' or 'stopped'. It distinguishes itself from sibling 'check_ocr_status' by being a minimal, token-saving alternative, making the purpose and unique value immediately apparent.

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

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

Explicitly recommends using this tool for high-frequency polling scenarios to save tokens, and identifies 'check_ocr_status' as the alternative when more detail is needed. This provides clear when-to-use and when-not-to-use guidance.

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