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

With no annotations provided, the description must fully disclose behavioral traits. It reveals that content is auto-converted to HTML and line breaks/spacing are preserved. However, it omits details about error behavior (e.g., invalid parent_key), authentication requirements, rate limits, or confirmation of creation success. The mutation nature is implied but not explicitly stated.

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 three sentences with no wasted words: first sentence states purpose and formatting, second lists use cases, third explains behavior. It is front-loaded with the primary action and remains succinct.

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 simplicity (3 parameters, 1 required) and the existence of an output schema, the description covers the essential context: purpose, use cases, and key parameter behaviors. It does not describe the return value, but the output schema likely fulfills that. A brief mention of what to expect upon creation 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?

Schema description coverage is 0%, so the description must compensate. It explains that 'Content is auto-converted to HTML' (adding meaning to the content parameter) and that parent_key attaches to a paper for organization. However, it does not mention the tags parameter or provide any syntax or constraints, leaving a 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 verb 'Create' and resource 'note in Zotero', specifies formatting support (tables, lists, line breaks), and lists concrete use cases (literature reviews, summaries, research memos). It distinguishes itself from sibling tools, which are all retrieval-oriented (get, search), making its 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 clear usage guidance: 'Use for: saving literature reviews, summaries, research memos, or any content' and 'Attach to a paper with parent_key for organized reference management.' It does not explicitly state when not to use or compare to alternatives, but since all siblings are read-only, exclusions are implicitly 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?

Description says 'List all' but schema has limit default 25, implying pagination. Fails to disclose that results may be truncated. With no annotations, this is a notable 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?

Two efficient sentences: first states purpose, second adds filtering behavior and downstream usage. No fluff, front-loaded.

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

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

Covers main workflow, but lacks explanation of limit/pagination and does not clarify that only keys are returned (though output schema may cover structure). Adequate but not comprehensive given no annotations.

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 crucial meaning for item_type parameter (default papers only, use '' for notes). But does not explain collection_key or limit; given 0% schema coverage, description partially compensates but not fully.

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 it lists papers/references in a collection, with default filtering. Distinguishes purpose from sibling tools by specifying output keys for use with get_item_metadata or get_item_children.

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

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

Provides guidance on using item_type parameter to include notes, and suggests subsequent tools for citation metadata or highlights. Could be more explicit about when not to use this tool vs zotero_search_items.

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

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

No annotations provided, so description carries full burden. It states the tool shows hierarchy and organization, but does not disclose details like pagination, rate limits, or that it is a read-only operation. Adequate but limited.

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?

Three concise sentences, all front-loaded with purpose and usage guidance. 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?

The description lacks details about the 'limit' parameter and does not explain the output format despite having an output schema. For a list tool, omitting behavior of the only parameter is a gap.

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

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

Schema coverage is 0% and the description does not mention the 'limit' parameter at all. The description adds no value beyond the schema's parameter outline, which itself has no 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 lists all folders/collections with hierarchy, using specific verb 'list' and resource 'folders/collections'. It distinguishes from sibling tools like zotero_get_collection_items which focuses on items within a collection.

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 mentions using the collection key with get_collection_items to browse papers, providing clear alternative usage. It does not explicitly state when not to use this tool, but the guidance is helpful.

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 carry the burden. It describes the return content in detail (highlights, colors, margin comments, notes), suggesting a read-only operation. However, it does not explicitly state it is non-destructive or mention any side effects, rate limits, or authentication needs.

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

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

The description is two sentences, front-loaded with the action, and every sentence adds value. No extraneous 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?

While the description explains the return content well, it omits critical context: the parameter 'item_key' is unexplained, and the output schema is not referenced. For a simple tool with 1 param, the description is incomplete.

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, and the description fails to explain the single required parameter 'item_key'. It does not provide any context on what it is or how to obtain it, leaving the agent without necessary information.

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 ('Retrieve... annotations and notes') and the resource ('a paper'). It distinguishes from siblings by specifying the return of highlights with colors, margin comments, and notes. However, the tool name 'item_children' is broader than 'annotations and notes,' causing a slight mismatch.

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 usage context ('Essential for literature_review prompt') but does not explicitly compare to siblings like zotero_search_annotations or specify when not to use this tool. The guidelines are implicit rather than direct.

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 that long papers are truncated and suggests asking about specific sections, which is key behavioral info. Lacks explicit mention of being read-only or requiring PDF access, but 'Extract and read' implies non-destructive.

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

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

Two sentences, front-loaded with verb and object. No wasted words. First sentence states core purpose, second adds usage guidance and a behavioral note.

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?

Has output schema but no annotations. Description provides basic purpose and truncation info but omits parameter explanations, preconditions (item must have PDF), and whether it's read-only. Adequate but not thorough for a 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?

Schema has 2 parameters with 0% description coverage. Description does not explain item_key (required identifier) or max_chars (optional limit). Schema property names are somewhat self-explanatory, but the description should clarify them for reliable use.

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 full text from PDF papers, using specific verb 'Extract and read' and resource 'full text content from a PDF paper'. It distinguishes from sibling tools like zotero_get_item_metadata (which likely returns metadata/abstract) and search tools.

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 says 'Use when you need to analyze the actual paper content beyond the abstract', which guides when to invoke. Also mentions truncation for long papers, implying when to ask for sections. Does not explicitly exclude other use cases or mention alternatives, 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?

No annotations are provided, so the description carries full burden. It describes the output (metadata fields) but does not mention any side effects, permissions, or error conditions. However, for a read-only metadata retrieval tool, this is largely sufficient and adds context beyond the bare schema.

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

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

Two compact sentences plus a tip, front-loaded with purpose and output details. No redundant words; 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?

An output schema exists (unseen) but the description lists key return fields. It lacks details about required input validation or error conditions, but the presence of sibling tools and the specific purpose make it adequately complete for a metadata retrieval 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%, requiring the description to explain parameters. The description does not mention `item_key` (what it identifies) or `include_bibtex` (what it does). It only describes the return values, leaving parameter meaning entirely to the schema 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?

Clearly states the tool retrieves complete bibliographic metadata for academic citation and analysis. Lists specific fields returned (title, authors, abstract, journal/venue, DOI, date, tags). Differentiates from sibling tools by explicitly mentioning alternatives for annotations (get_item_children) and full text (get_item_fulltext).

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 tells when to use alternative tools: 'For reading annotations...use get_item_children; for full text use get_item_fulltext.' Also advises using a dedicated prompt for literature reviews instead of ad-hoc analysis, providing clear usage boundaries.

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, description explains default behavior (papers only, sorting by dateModified) and how to modify it. Discloses that it returns recent items, but doesn't explicitly state it is read-only or mention pagination. Still, clear and consistent.

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

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

Two sentences only; first sentence clearly states purpose, second sentence provides critical parameter guidance. No wasted words, front-loaded effectively.

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 main use cases and parameter behavior. Output schema exists so return details aren't needed. Could mention that results are a subset of library items, but overall adequate for a simple 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% description coverage, but description adds meaning for sort_by and item_type (e.g., 'dateModified' for reading activity, 'dateAdded' for imports, default excludes notes). Doesn't explain limit, but its purpose is obvious.

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 uses specific verb 'Get' and resource 'recently read, modified, or imported papers from your library', clearly distinguishing it from general search tools. The name 'get_recent' aligns with the behavior.

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

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

Provides guidance on when to use different parameter values (e.g., sort_by='dateAdded' for imports, item_type='' for notes), but does not explicitly compare to sibling tools like zotero_search_items or mention 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?

With no annotations provided, the description effectively discloses behavioral traits: it searches all annotations and comments across all papers, returns highlighted text, comments, page numbers, and parent paper context. It does not detail ordering or pagination, but the core behavior is 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?

The description is concise at 5 sentences, front-loaded with the core functionality, followed by return details and use cases. 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 the presence of an output schema, the description adequately covers the return values and the search scope. It lacks mention of result ordering or maximum results, but overall it sufficiently explains the tool's purpose and output for 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 coverage is 0%, so the description must clarify parameters. It describes 'query' as a keyword, which is helpful, but neither 'limit' (default 50) is mentioned nor its purpose explained. The description adds no value beyond what the schema property names imply.

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 annotations across the entire library by keyword, specifying the types (PDF, EPUB, snapshot) and including your comments. It distinguishes itself from siblings like zotero_search_items by focusing on annotations and comments rather than item metadata.

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 lists use cases: cross-paper knowledge synthesis, finding where a concept was discussed, building thematic connections. While it doesn't explicitly say when not to use it or compare to siblings, the use cases provide clear guidance for appropriate scenarios.

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 that the tool searches and returns item keys, and describes two search modes. However, it does not explicitly state that the operation is read-only (implied but not confirmed), nor does it mention any rate limits or other behavioral traits.

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

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

Two sentences with clear front-loading. Every sentence adds value: first states purpose, second explains modes and follow-up. 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 search tool with an output schema, the description covers the primary purpose and usage. It explains two qmodes and directs to related tools. However, it omits details about default item_type (excludes attachments) and pagination via limit, which would help completeness given the 5 parameters.

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

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

Schema coverage is 0%, so description must compensate. It adds value by explaining qmode options ('titleCreatorYear' default vs. 'everything') and the return type (item keys). But it does not describe the purpose of item_type, limit, or tag parameters, leaving gaps for a 5-parameter tool.

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 searches a reference library by keyword and specifies the resource type (papers, articles, books, notes). It connects to sibling tools by mentioning item keys for get_item_metadata or get_item_children. However, it could more explicitly differentiate from zotero_search_annotations, which searches 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?

Provides clear guidance on when to use default vs. 'everything' qmode, explaining that default searches title/author/year while 'everything' searches full text and note contents. Also informs the agent about subsequent tools to use (get_item_metadata or get_item_children). Does not explicitly state when to avoid this tool in favor of others like list tools.

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