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

With no annotations, the description carries full transparency weight. It discloses behavioral traits: output is saved as a Canvas file in the vault, Mermaid is returned, and the slug defaults to anchor.arxiv_id. This is sufficiently transparent for a visualization tool.

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 brief purpose statement, a direction clarification, and a clear arg list. It is not overly verbose, though it could be slightly more concise by omitting redundant schema-like details already covered.

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 (nested objects, 5 params, output schema exists) the description covers the main aspects: flow direction, file saving, and arg defaults. It does not explain return values explicitly, but output schema covers that. Minor missing detail on how to retrieve Mermaid output.

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 detailed structures for anchor (fields), ref_groups, and cite_groups (topic and papers arrays), and clarifies direction options and slug fallback. This adds 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 the tool's purpose: producing a visualization using an anchor and topic groups of references and citations. It distinguishes itself from sibling tools by explicitly mentioning Mermaid (response) and Canvas (vault save), which are unique to this tool.

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 parameter details but lacks explicit guidance on when to use this tool versus alternatives like get_citation_contexts or get_citations_by_citations. Usage is implied through the arg descriptions, but no when-not-to-use or comparison is 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?

The description discloses the key behavior of caching (skip redownload if already saved) and that it returns a path. Since no annotations are provided, this adds helpful context beyond the 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?

The description is concise with two short paragraphs, front-loading the main purpose and caching behavior, followed by parameter details. No redundant sentences.

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 one-parameter tool, the description covers the main functionality and parameter details adequately. It does not explain the output schema, but that is acceptable as per guidelines since 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?

The description adds significant meaning to the single parameter 'paper_id' by providing an example format, noting that prefixes like 'ARXIV:' and version suffixes are allowed. This compensates for 0% schema description 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 downloads arXiv paper PDFs to local storage and returns the file path. It distinguishes itself from siblings like 'read_paper' by focusing on downloading rather than reading or displaying.

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 when to use (when needing a local PDF) and mentions caching behavior, but it does not explicitly state when not to use or contrast with sibling tools like 'get_paper_by_id' or 'read_paper'.

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 carries full burden. It discloses the storage path pattern and fallback behavior for the slug parameter, but does not cover behaviors like overwrite policy, handling of uncached PDFs, 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 efficiently structured: two sentences for purpose and a clear parameter list. Every line 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 the tool's simplicity (2 params, output schema provided), the description covers key aspects: what it does, where it saves, and fallback behavior. It lacks error conditions but is sufficient for a focused extraction 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?

With 0% schema description coverage, the description compensates by explaining both parameters: paper_id (arXiv ID for PDF cache lookup) and slug (vault directory name, with fallback). This adds meaningful context 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 verb 'save' and the resource 'caption-matched raster figures from cached PDF'. It specifies the storage location and distinguishes the tool from siblings like 'extract_paper_tables' by focusing on figures.

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 such as 'prune_paper_figures' or 'get_paper_by_id'. The description mentions ADR references but does not provide usage context or exclusions.

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 the tool saves to vault, uses region crop, captures caption+area, notes the impossibility of sub-image separation due to vector text, and specifies the naming convention. This provides substantial behavioral context.

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 includes technical details like ADR-018 and a thorough explanation of the extraction limitation, which adds length. It is structured with bullet points for args, but could be more concise by moving some technical rationale to a 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?

Given the tool's complexity (PDF extraction, vault storage) and the presence of an output schema, the description covers storage location, method, limitation, and parameter semantics. It addresses the essential aspects for an agent to use the tool 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?

Schema coverage is 0%, so the description must compensate. It does: paper_id is explained as arXiv ID, slug as vault directory name with default use of arxiv_id. This adds meaning beyond the schema, though the description does not explicitly mention that slug is optional.

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 tables from cached PDFs based on captions, saves them as PNGs to the vault, and specifies the storage location. It distinguishes from siblings like extract_paper_figures by mentioning the specific method (region crop) and technical limitation (vector 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 implies usage for extracting tables from cached papers but does not explicitly state when to use this tool versus alternatives like extract_paper_figures or when to avoid it. No context on prerequisites or conditions.

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 does not disclose whether the tool is read-only, requires authentication, or has side effects. The description only states it returns snippets, with no behavioral guarantees.

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 two-sentence overview followed by an Args list. Each 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 tool has an output schema (not shown), the description need not detail return values. It explains the purpose, usage context, and parameters adequately. Missing details like empty result handling or performance are minor given the output schema's expected coverage.

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 no descriptions (0% coverage), but the description adds meaning by explaining both parameters: citing_id is the citing paper (arXiv ID / DOI / SS sha) and cited_id is the cited paper. This provides necessary context 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 returns citation context snippets between two papers, specifying the exact resource and action. It distinguishes itself from siblings like get_citations_by_citations by focusing on context snippets rather than citation counts or references.

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 the tool is used as input for dynamic topic analysis (ADR-009), giving a specific use case. However, it does not directly compare with sibling tools or state when not to use it.

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?

The description fully discloses key behaviors: default sorting (velocity), the SS endpoint's descending publicationDate order, the effect of exclude_recent_year filtering, and the min_velocity threshold. This is excellent transparency given no annotations.

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 concise overview followed by a bulleted parameter list. The first paragraph is slightly technical but necessary. It is appropriately sized for the complexity.

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

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

Given the tool's complexity (7 parameters, sorting logic, filtering), the description covers all essential aspects: purpose, parameter meanings, behavioral quirks, and output context. An output schema exists, so return value details are not needed.

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

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

With 0% schema description coverage, the description explains all 7 parameters including defaults, acceptable values (e.g., paper_id formats), and functional effect (e.g., exclude_recent_year removes recent year). This fully 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 action: sorting and returning subsequent studies that cited a paper. It specifies the resource (citations of a paper) and distinguishes it from siblings like get_references_by_citations or get_citation_contexts.

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 the issue with the SS API's default sorting and why exclude_recent_year is used, implying when to set that parameter. However, it does not explicitly compare against sibling tools or provide when-to-use/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.

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 results are ordered by popularity and includes a default limit, but lacks details on error handling, rate limits, or authentication requirements. The mention of a fallback chain hints at reliability but is 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?

Extremely concise: two sentences in the main description plus two lines for parameters. Front-loaded with the main action, then direct parameter details. 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?

Given the output schema exists and parameters are fully explained, the description is almost complete. It could mention that the tool is read-only or clarify the fallback chain, but these are minor omissions. No major 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 documentation coverage is 0%, so the description must fully explain parameters. It clearly specifies the date format (YYYY-MM-DD), that blank defaults to today UTC, and limit meaning top N with default 10. This adds essential meaning 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 retrieves 'Hugging Face Daily Papers' and returns them in popularity order. This verb+resource combination is specific and distinguishes it from sibling tools like search_papers or get_paper_by_id.

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?

Implied usage is to fetch daily papers sorted by popularity, but there is no explicit guidance on when to use this tool versus alternatives such as search_papers or get_recommended_papers. The cryptic mention of 'ADR-006 fallback chain' is not helpful for decision-making.

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 states the action (retrieve details) and supported IDs, but does not disclose behavioral traits like authorization requirements, rate limits, or what 'details' include. The output schema likely covers return structure, but the description lacks explicit behavioral context.

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 relatively concise with the main purpose stated first. The 'Args:' section adds necessary detail but is slightly longer than needed. Overall, it is well-structured and 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?

Given the tool has only one parameter and an output schema (not shown), the description adequately covers what the tool does and the parameter formats. It is complete for a simple lookup tool, especially with the presence of an output schema defining the return values.

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

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

The schema provides no description for the paper_id parameter (0% coverage). The description compensates by listing example formats for arXiv ID, DOI, and Semantic Scholar SHA ID, adding meaning beyond the type string alone.

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 verb (조회=retrieve) and resource (논문 상세 정보=paper details). It specifies support for multiple ID types (arXiv, DOI, Semantic Scholar SHA), distinguishing it from sibling tools like search_papers which search by query.

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?

Description explains which IDs are supported, implying usage when you have a known paper ID. However, it does not explicitly state when to use this tool over alternatives, such as when to use search_papers instead. The support for three ID types provides good 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; description mentions 'content similarity' but lacks details on side effects, auth, or output format. Adequate but not thorough.

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?

Front-loaded with purpose, then context, then parameters. No wasted words; efficiently structured.

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 output schema exists, description covers purpose, usage guidance, and parameter semantics. Lacks mention of limitations like data freshness, but overall 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?

Adds concrete meaning beyond schema: paper_id accepts arXiv ID, DOI, or S2 ID; k described as recommendation count with default. 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?

Describes specific verb 'returns' and resource 'recommended papers based on content similarity'. Clearly distinguishes from citation-based sibling 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 states when to use (new topic exploration, discovering related fields) and when not (citation-centered workflow). Implies alternatives like citation 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?

With no annotations, the description carries full burden. It discloses sorting modes (velocity with ADR-004 reference), threshold for noise removal (min_velocity), and typical reference counts (most papers < 100). This provides good behavioral insight beyond the 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?

The description is well-structured with an args list, but slightly verbose with repeated default indicators. It could be more compact while retaining clarity. However, it remains efficient and front-loaded with the main purpose.

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

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

Given the output schema exists, the description covers all input parameters and key behavioral traits. It explains velocity computation and practical limits. The absence of error handling or return format details is acceptable given output schema, but some context on expected output could elevate 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%, but the description adds extensive detail for all 6 parameters: paper_id formats (arXiv, DOI, Semantic Scholar ID), defaults, sort options (velocity vs count), and the significance of min_velocity. This far exceeds baseline compensation.

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

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

The description clearly states the tool returns sorted papers referenced by a given paper. It uses a specific verb ('returns') and resource ('referenced papers'), and is distinct from sibling tools like get_citations_by_citations which likely returns citing papers.

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 parameters and behavior but does not explicitly state when to use this tool versus alternatives like get_citations_by_citations or search_papers. Usage context is implied but not directly addressed with when-not or alternative suggestions.

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 full burden. It states the tool deletes files (destructive action) but does not emphasize irreversibility or permission requirements. The behavioral context is adequate but could be stronger.

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 single-sentence summary followed by usage context, then parameter details. It is concise without wordiness, though the parameter list 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 the moderate complexity (3 params, one list) and presence of an output schema (not shown), the description covers the intended workflow and parameter behaviors. It lacks error handling or return value details but is sufficient for common 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%, but the description compensates thoroughly: explains 'paper_id' for normalization, 'keep' allows two formats and empty list means delete all, 'slug' falls back to arxiv_id for legacy compatibility. This adds significant meaning beyond the schema.

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

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

The description clearly states the tool prunes figures by deleting all except those in 'keep', specifying the directory path. It uses a specific verb and resource, and distinguishes from siblings like 'extract_paper_figures' and 'prune_paper_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 provides context: the tool is intended to be called after 'extract_paper_figures' with a selected list of figures. It references ADR-015/016 for context. However, it lacks explicit when-not-to-use guidance compared to alternatives.

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 must carry the full burden. It states the tool deletes files from a vault directory based on a keep list, making the destructive nature clear. However, it does not disclose whether deletions are permanent, if there are rollback options, or any authorization requirements. The explanation is minimal but adequate for a simple file deletion 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 extremely concise: one sentence for overall purpose followed by a bullet-point list of parameters. Every element serves a purpose with no redundancy. The most critical information is front-loaded, making it easy for an agent to parse quickly.

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

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

The tool has 3 parameters, an output schema (not shown), and no nested objects. The description covers the core function and parameter meanings but omits details like default behavior (e.g., what if slug is null?), edge cases (empty keep list), or consequences of the deletion. It is just sufficient for an agent to understand what to expect, but not comprehensive.

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 clearly explains each parameter: paper_id (arXiv ID), keep (list of file identifiers with examples), and slug (vault directory name). This adds meaningful context that the schema lacks, meeting the need for compensation.

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

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

The description clearly states the tool's function: prune (delete) table files in a vault directory, keeping only those specified in 'keep'. It identifies the specific resource (papers/<slug>/tables/) and the action (delete all except listed). This distinguishes it from siblings like prune_paper_figures and extract_paper_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?

No guidance on when to use this tool versus alternatives (e.g., prune_paper_figures). The description does not mention prerequisites, when not to use, or typical scenarios. Usage context is only implicit from the tool name and action.

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 the full burden of behavioral disclosure. It mentions caching behavior (cache hit vs miss) and the meaning of max_pages=0 (full text). However, it does not disclose what happens if the PDF is inaccessible, any required permissions, or the format of the extracted text.

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 for purpose and process, then bullet-style argument explanations. No extraneous words. Every sentence provides 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 that an output schema exists (so return values need not be explained), the description covers the main functionality well. It specifies the tool only works for arXiv papers, describes the caching mechanism, and explains both parameters. Minor gap: could mention that extracted text is plain text, but overall sufficient for a simple 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?

The input schema provides minimal information (no descriptions for parameters). The description adds clear semantics: paper_id is an arXiv ID with an example ('2301.12597'), and max_pages is explained as max pages to extract with 0 meaning full text. This fully compensates for the 0% schema description 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 extracts full text from arXiv PDFs with caching. It uses a specific verb ('extract') and identifies the resource ('arXiv paper PDF'). This differentiates it from sibling tools like 'download_paper' which presumably only downloads without extracting 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 implies usage via the action and input schema but does not explicitly state when to use this tool versus alternatives like 'get_paper_by_id' (which may return metadata) or 'download_paper'. No exclusion criteria or alternative guidance is provided.

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

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

No annotations provided, so description must carry full burden. It explains the action (render and save) and default DPI, but lacks disclosure of potential side effects (e.g., overwriting, vault space usage) or error conditions.

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?

Concise with a clear structure: brief purpose statement followed by bullet-point parameter list. No redundant sentences. Efficient use of space.

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?

Output schema exists, so return values need not be explained. However, the description omits details like error handling, prerequisite checks (paper downloaded?), and vault storage behavior. Adequate but not comprehensive.

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's Args section adds meaning to each parameter (e.g., 'arXiv ID', '1-base page number', 'vault directory name'), significantly improving understanding beyond the schema.

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

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

Description clearly states the tool renders a PDF page as PNG and saves to vault. References ColPali style and distinguishes from figure crop tools, making purpose specific and distinct from siblings like extract_paper_figures.

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 mentions when to use ('figure crop misses' or 'preserve math-heavy pages'), providing context. Does not explicitly state when not to use, but the guidance is clear enough given the sibling 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 the full burden. It reveals that results are sorted by relevance and categorized by time range (1/3/5 years), which adds behavioral context. However, it does not mention rate limits, authentication requirements, or potential side effects, leaving some transparency gaps.

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 main sentence followed by parameter details. Every sentence contributes useful information. There is no fluff, though it could be slightly more structured with a brief behavioral note upfront.

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 detail return values. It adequately covers the input parameters and mentions key behaviors (sorting, categorization). The tool is simple, and this description is sufficient for an 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 description provides explicit meaning for each parameter in the Args section, including examples and constraints (e.g., max_results default 20, max 50; category example 'cs.CV'). This adds significant value beyond the schema, which has no descriptions (0% 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 the tool searches arXiv papers by topic/keyword, with sorting by relevance and categorization by time range. It distinguishes itself from sibling tools like get_paper_by_id or get_recommended_papers, which serve different purposes.

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 guidance on when to use this tool versus alternatives, nor does it mention conditions where it should not be used. It only states what it does without contextual usage advice.

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?

The description explains the action (add line at end) and duplicate handling (skip if exists). However, it does not disclose effects if source note does not exist, permissions needed, or any side effects. With no annotations, the description carries full burden but is somewhat adequate for a simple append 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 a parameter list. It has no unnecessary words, but the first sentence is in Korean which may reduce accessibility. The structure is functional but not overly polished.

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 annotations are absent and the output schema exists but is not described, the description does not cover return values or error handling. It is sufficient for the core task but lacks completeness for a full tool understanding.

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 provides essential meaning: source and target are note slugs, note is an optional one-line description. This adds significant value beyond the bare schema, though it could clarify that 'note' is appended next to the link.

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 adds a wikilink line to the end of a source note's body and skips duplicates. The verb 'add' and resource 'source note' are specific. It implicitly distinguishes from siblings like wiki_write_note (which writes full note content) but does not explicitly contrast.

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

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

No guidance is provided on when to use this tool versus siblings like wiki_list, wiki_read_note, or wiki_write_note. There is no mention of prerequisites or scenarios where this tool is appropriate or inappropriate.

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 only states the tool lists notes, but lacks disclosure of behavioral traits like idempotency, error handling (e.g., invalid prefix), or whether listing is recursive.

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—with the purpose front-loaded. Every word serves a purpose; 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?

The tool is simple with one parameter and an output schema (not shown). However, additional context about file types, recursion depth, or behavior on missing directories would improve completeness. Adequate for a basic listing 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 'prefix' parameter as 'vault root 기준 디렉토리' (directory relative to vault root) with default 'papers', adding meaning beyond the schema's basic type definition. Schema coverage is 0%, so this clarification is valuable.

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 notes in a vault directory, using 'vault 안 디렉토리의 노트 목록' and gives examples (papers/topics/digests). It distinguishes from siblings like wiki_read_note and wiki_write_note, though not from search_papers explicitly.

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?

Usage is implied through the description of listing notes in a directory with a given prefix. No explicit guidance on when to use vs. alternatives or when-not-to-use is provided.

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

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

No annotations provided, and description does not disclose behavioral traits such as read-only nature, performance characteristics, or any side effects. Implies read operation but not explicit.

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 with two clear parts: purpose and parameter explanation. Front-loaded with purpose. Could be slightly more structured but 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?

Describes input parameter well but missing output format details and usage context. Has output schema but description doesn't reference it. Adequate for a simple tool but could be improved with usage tips.

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?

Parameter 'slug' is well-explained: it can be an arxiv_id or a relative path. This adds significant value beyond the schema's type definition, especially with 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?

Description clearly states the tool retrieves the full text of an Obsidian note including frontmatter. The verb '조회' (retrieve) and resource '노트' (note) are specific. Distinguishes from siblings like wiki_write_note, wiki_list, 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?

No guidance on when to use this tool versus alternatives like search_papers or get_paper_by_id. Does not specify prerequisites or 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?

Discloses folder auto-creation and frontmatter parsing behavior (JSON string fallback). However, does not mention whether it overwrites existing notes or appends, which is important for a write 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?

Description is concise with a short summary followed by parameter details. The bullet-like listing is efficient, though the parameter descriptions are embedded in prose.

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 an output schema exists (not shown), return values are not required. However, the description lacks error handling details, permission requirements, and behavior on duplicate slugs. It adequately covers basic functionality.

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 slug as 'arxiv_id or vault relative path', frontmatter as 'dict for YAML serialization with JSON parsing', and body as 'markdown'. This adds meaning but could be more precise (e.g., what is vault?).

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 saves a note with frontmatter and body, and auto-creates folders. This is distinct from sibling tools like wiki_read_note and wiki_list, which are read/list operations.

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 clearly indicates this tool is for saving notes, but does not explicitly state when not to use it or provide alternatives. However, the context of sibling tools implies differentiation.

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