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

Discloses write operation, need to close Zotero, and refresh requirement. No annotations provided, so description bears full burden and does well.

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 separate sections (description, note, Args). Could be slightly more concise, but 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?

Covers purpose, parameters, post-usage steps, and behavioral notes. Output schema is present but description is self-sufficient for a simple 2-param 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?

Adds meaning beyond schema: describes parent_item_id as numeric string representing item ID, and note_content as HTML/plain text with Markdown support. Schema had 0% coverage, so this is essential.

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 creating child notes for Zotero items, a specific verb+resource. Distinguishes from sibling tools like batch_annotate or create_pdf_annotation.

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 post-write refresh requirement and note about needing to close Zotero. Lacks comparison to sibling tools but gives clear context for usage.

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 must cover behavioral traits. It discloses that it is a write operation and requires closing Zotero. However, it does not mention idempotency, partial failure handling, rate limits, or the format of the return value (though an output schema exists). This leaves gaps in behavioral understanding.

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 no unnecessary words. It front-loads the main purpose in the first line, then provides a prerequisite, followed by a structured argument list that is easy to scan. 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?

The description covers purpose, usage prerequisite, and parameter details adequately. However, it lacks information about the output (e.g., what is returned, success/failure per annotation) and any limitations like maximum batch size or error behavior. While an output schema exists, the description should at least hint at the return structure for 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?

Despite 0% schema description coverage, the description adds substantial meaning to both parameters. For 'item_id', it explains it can be a Zotero PDF attachment itemID (number) or an absolute PDF path. For 'annotations', it provides a clear template structure with fields like page_index, rects, color, etc., which is far beyond the bare schema type.

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: '一次性创建多条 PDF 标注（减少调用次数）' (create multiple PDF annotations at once to reduce calls). It specifies the verb 'create', the resource 'PDF annotations', and the benefit of batching. This distinguishes it from the sibling tool 'create_pdf_annotation' which presumably creates single 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 provides a clear prerequisite: '写操作需要关闭 Zotero 桌面应用' (write operation requires closing Zotero desktop app). It implies when to use this tool (when creating multiple annotations to reduce calls) but does not explicitly state when not to use it or suggest alternatives like 'create_pdf_annotation' for single annotations.

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 fully carries the burden. It discloses important behaviors: the operation modifies the PDF, requires a refresh/restart to become visible, and necessitates closing Zotero during write. This goes well beyond basic functionality.

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 a clear purpose first, then usage notes, then parameter list. It is somewhat lengthy due to detailed parameter explanations, but every sentence adds value. A slight trim could improve conciseness.

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

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

The description covers the prerequisite (get_pdf_layout_text), the operation, and post-operation steps (restart/refresh). It also warns about the database lock. However, it does not describe the output or error handling, though an output schema exists.

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 explains each parameter in detail, adding meaning: item_id can be ID or path, rects come from get_pdf_layout_text, color with examples, and type default. This provides crucial guidance missing from 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 it creates highlight/underline annotations on Zotero PDFs. The verb 'create' and resource 'annotation' are specific, and it distinguishes from sibling tools like list_annotations or get_pdf_layout_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 explicit context: coordinates should come from get_pdf_layout_text, and it warns about needing to restart or refresh after writing. It also advises closing Zotero to avoid database lock. However, it does not compare with batch_annotate or specify when not to use this tool.

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

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

No annotations are provided, so the description must cover behavioral traits. It explains that it accepts item IDs or PDF paths and automatically finds parent items, which is useful. However, it does not disclose error handling, authentication needs, or any side effects of the 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 two sentences and an arguments line. It is front-loaded with the main purpose. It could be more structured (e.g., bullet points for args), but the current format is efficient and clear.

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 that an output schema exists, the description does not need to explain return values. It covers the input types adequately and mentions key metadata fields. However, it omits information about error scenarios or prerequisites, which would enhance 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?

The single required parameter item_id has no schema description (0% coverage), but the description adds significant meaning: it specifies that the input can be a numeric itemID or a PDF file path, and that it works for both items and PDF attachments. This compensates well for the lack of schema-level 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 it retrieves complete metadata for a Zotero item, listing returned fields (title, authors, year, journal, DOI). It distinguishes from sibling tools like list_zotero_items and search_zotero_items by focusing on a single item's full metadata, but does not explicitly differentiate.

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 indicates it supports item IDs or PDF attachment IDs, but does not provide explicit guidance on when to use this tool versus alternatives (e.g., search_zotero_items for multiple items). No exclusion criteria or context for optimal use are given.

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

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

No annotations provided, so description carries full burden. It discloses return format (JSON with text and rect), coordinate system, and parameter details. Lacks info on error handling or side effects, but overall transparent.

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?

Description is concise but includes an Args section that partly repeats schema info. However, it adds value (type clarifications) and is well-structured in front-loaded style.

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 low complexity (2 params, clear output described), the description covers essential aspects: input, output format, and usage hint. No critical 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 coverage is 0%, so description adds crucial meaning: item_id can be numeric Zotero itemID or file path, page_number is 0-indexed. This fully compensates for schema's lack of description.

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 it extracts text and physical coordinates from a specified PDF page, with a specific verb 'extract' and resource 'PDF page'. It distinguishes itself from siblings like get_pdf_text_bulk and create_pdf_annotation.

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?

Mentions that rect can be used with create_pdf_annotation, implying a use case, but does not explicitly state when not to use or compare to alternatives like get_pdf_text_bulk.

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?

Without annotations, the description covers key behaviors: extraction is pure text without coordinates, context usage is reduced by ~80%, and skip_refs defaults to true. However, it does not mention error handling for invalid item_ids or page ranges.

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

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

The description is well-structured with purpose first, then differentiation, then workflow, then args. It is concise but the workflow section is slightly verbose. Overall efficient.

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

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

Given the presence of an output schema, the description does not need to detail return values. It covers purpose, parameters, differentiation from siblings, and usage workflow adequately, making it complete for the agent's decision-making.

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 each parameter: item_id as Zotero itemID (number) or file path, pages as 0-indexed list with default of all pages, skip_refs as boolean to skip references with default true. This adds substantial meaning beyond the bare 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 extracts plain text from PDF pages without coordinates, specifically for large PDF content understanding. It distinguishes from the sibling get_pdf_layout_text by noting the absence of coordinates and reduced context usage.

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 specifies when to use this tool (bulk text extraction) and provides a recommended workflow: first use this for full text, then get_pdf_layout_text for coordinates on target pages, then create_pdf_annotation. Also mentions the difference from get_pdf_layout_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?

Although no annotations are provided, the description explains what the tool returns (type, color, text, comment) and the acceptable argument format (itemID or file path). It does not mention side effects or permissions, but for a list operation, this level of detail is adequate.

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 clear title line, a usage sentence, a summary of return content, and a precise parameter explanation. 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?

Given the output schema exists, the description need not detail return values but still does. It covers the tool's purpose, usage, parameter format, and return content, making it complete for an agent to select and invoke 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?

With 0% schema description coverage, the description fully compensates by explaining that item_id can be a Zotero PDF attachment itemID (number) or an absolute file path, adding significant meaning beyond the bare 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 it lists all annotations on PDF attachments and provides a use case (checking existing annotations to avoid duplicates). However, it does not differentiate itself from sibling tools like batch_annotate or create_pdf_annotation.

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 explicitly says it is used to check existing annotations to avoid duplicates, providing clear usage context. It does not mention when not to use or list alternatives, but the implied guidance is sufficient.

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 must disclose behavior. It states the operation (list), return fields, and limit parameter. However, it does not mention pagination, ordering, authentication needs, or potential performance implications for large libraries.

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: 4 short sentences in Chinese. It front-loads the main action, lists returns, gives purpose, and explains the parameter. No wasted words.

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

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

For a simple list tool with one optional parameter and an output schema, the description covers input and basic output. But it omits return format details, sorting, and error handling. Output schema exists but is not shown; description still incomplete on behavior.

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 explains the only parameter 'limit' with default 50 and meaning (max number of items returned). This compensates fully for the schema gap, though no other parameters exist.

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 lists Zotero library entries and specifies returned fields (itemID, key, title, PDF attachment ID). It distinguishes itself from sibling 'search_zotero_items' by implying a full list with limit, not a search filter.

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 mentions it is used to discover item_id for other tools, but lacks explicit guidance on when to use it versus alternatives like search_zotero_items. No when-not or exclusion criteria 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 provided, so description carries full burden. It only describes search capability without disclosing any behavioral traits such as authentication needs, rate limits, or behavior on no results. Minimal additional context beyond purpose.

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

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

Two-sentence description plus parameter list is compact and front-loaded. Every sentence provides 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?

Parameters are simple, output schema exists (not detailed but present), and the tool is straightforward. Description covers purpose and key parameter meanings adequately for a search 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 has 0% parameter descriptions, but the description explains 'query' as search keyword (partial title/author/Zotero key) and 'limit' as max return count (default 20). This adds meaningful meaning beyond the bare 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?

Description clearly states the tool searches Zotero items by title, author, or key, and explicitly contrasts with sibling tool 'list_zotero_items' as more efficient for direct targeting. This provides a specific verb+resource and distinguishes from 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?

Explicitly states when to use this tool over 'list_zotero_items' (more efficient for direct targeting). However, lacks explicit when-not-to-use or alternative scenarios beyond the sibling.

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