Server Quality Checklist

Tool Scores

• add_to_libraryC
  2.9/5.0
  Behavior2/5

  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 implies a write operation ('Add') but doesn't disclose behavioral traits such as permissions required, whether additions are idempotent, error handling for invalid bibcodes, or rate limits. This is a significant gap for a mutation tool with zero annotation coverage.

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

  Conciseness5/5

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

  The description is appropriately sized and front-loaded with a clear purpose in a single sentence. Every word earns its place, with no redundant information, making it efficient and easy to parse.

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

  Completeness2/5

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

  Given the complexity of a write operation with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects (e.g., success/failure responses, side effects) and doesn't compensate for the absence of structured data, leaving gaps for an AI agent to understand the tool fully.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents both parameters ('library_id' and 'bibcodes'). The description adds minimal value by restating the parameters without providing additional context, such as format examples for bibcodes or how to obtain the library ID beyond referencing 'list_libraries'.

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

  Purpose4/5

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

  The description clearly states the verb ('Add') and resource ('papers to an existing library'), making the purpose specific and understandable. It distinguishes from siblings like 'create_library' (creates new) and 'list_libraries' (lists), but could be more explicit about differentiation from 'get_library_papers' (reads vs. writes).

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It mentions 'existing library' but doesn't specify prerequisites (e.g., library must exist), exclusions, or comparisons to siblings like 'create_library' for new libraries or 'search_papers' for finding papers to add.

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

• get_author_papersC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the return format but doesn't cover important aspects like whether this is a read-only operation, potential rate limits, authentication requirements, error conditions, or pagination behavior. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.

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

  Conciseness4/5

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

  The description is efficiently structured in two sentences that convey the core purpose and return format without unnecessary elaboration. It's appropriately sized for this type of lookup tool, though it could potentially be more front-loaded with key behavioral information given the lack of annotations.

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

  Completeness2/5

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

  For a tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the returned paper objects contain beyond 'citations and publication details', doesn't mention error handling, and provides no behavioral context. Given the complexity of academic paper data and the lack of structured metadata, more comprehensive guidance would be helpful.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema (like clarifying author name formats or result limitations). Baseline 3 is appropriate when the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the tool's purpose with specific verb ('Find') and resource ('papers by a specific author'), and mentions the return format ('list of papers with citations and publication details'). However, it doesn't explicitly differentiate from sibling tools like 'get_author_metrics' or 'search_papers', which might have overlapping functionality.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives like 'search_papers' or 'get_author_metrics'. It lacks context about prerequisites, exclusions, or comparative use cases with sibling tools, leaving the agent to infer usage based on tool names alone.

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

• get_library_papersC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool returns paper details but doesn't specify format, pagination, error handling, or performance aspects like rate limits. This leaves significant gaps in understanding how the tool behaves 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.

  Conciseness4/5

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

  The description is efficiently structured in two sentences, front-loaded with the core purpose and followed by return details. There's no wasted text, though it could be slightly more informative to improve completeness without losing conciseness.

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

  Completeness2/5

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

  Given no annotations and no output schema, the description is incomplete. It doesn't explain what 'paper details' includes, how results are formatted, or any behavioral traits like error cases. For a tool with one parameter but missing structured context, this leaves too many gaps for effective agent use.

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

  Parameters3/5

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

  The schema description coverage is 100%, with the parameter 'library_id' documented as 'Library ID (from list_libraries)'. The description adds minimal value beyond this, mentioning 'specified collection' which aligns with the schema but doesn't provide additional syntax or format details. Baseline 3 is appropriate as the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the action ('Get all papers') and resource ('from a specific library'), with the purpose being to retrieve paper details for a collection. It distinguishes from siblings like 'get_author_papers' or 'get_paper_details' by focusing on library-based retrieval, though it doesn't explicitly contrast them.

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

  Usage Guidelines2/5

  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 alternatives like 'search_papers' or 'get_author_papers', nor does it mention prerequisites such as needing a library ID from 'list_libraries'. The description implies usage for library-specific papers but lacks explicit context or exclusions.

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

• get_paper_detailsC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool 'Returns full metadata including abstract, authors, citations, keywords, and more,' which gives some output context, but lacks details on error handling, rate limits, authentication needs, or data freshness. For a read operation without annotations, this is a significant gap in transparency.

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

  Conciseness4/5

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

  The description is concise and front-loaded, stating the core purpose in the first sentence. The second sentence elaborates on return values efficiently. There's no wasted text, though it could be slightly more structured for clarity. It earns its place but isn't perfectly optimized.

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

  Completeness3/5

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

  Given the tool's low complexity (1 parameter, no nested objects) and high schema coverage, the description is adequate but incomplete. It lacks an output schema, so the description partially compensates by listing return metadata. However, without annotations and with sibling tools present, more context on usage and behavior would improve completeness for an AI agent.

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

  Parameters3/5

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

  The input schema has 100% description coverage, with the 'bibcode' parameter well-documented in the schema itself. The description adds minimal value beyond the schema by implying the bibcode is used to fetch paper details, but doesn't provide additional syntax, format nuances, or examples. This meets the baseline of 3 when schema coverage is high.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: 'Get detailed information about a specific paper using its bibcode.' It specifies the verb ('Get'), resource ('paper'), and identifier ('bibcode'), making the action clear. However, it doesn't explicitly differentiate from sibling tools like 'get_paper_metrics' or 'get_author_papers', which prevents a score of 5.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It mentions retrieving 'detailed information' but doesn't clarify if this is for metadata vs. metrics or how it differs from tools like 'get_paper_metrics' or 'search_papers'. No exclusions or prerequisites are stated, leaving usage ambiguous.

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

• create_libraryB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. While it states the tool creates something (implying a write operation), it doesn't disclose critical behavioral traits such as whether this requires specific permissions, if libraries are permanent or deletable, rate limits, or what happens on success/failure. The description adds minimal value beyond the basic purpose.

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

  Conciseness5/5

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

  The description is appropriately sized and front-loaded: the first sentence states the core purpose, and the second adds useful context without redundancy. Every sentence earns its place by clarifying the tool's utility, making it efficient and easy to parse.

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

  Completeness2/5

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

  Given the complexity of a creation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., library ID, success confirmation), error conditions, or behavioral nuances like idempotency. For a mutation tool, this leaves significant gaps for an AI agent to operate effectively.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the input schema already documents all three parameters (name, description, public) with clear descriptions and defaults. The description adds no additional parameter semantics beyond what's in the schema, such as format constraints or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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

  Purpose4/5

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

  The description clearly states the verb ('Create') and resource ('new paper library/collection'), making the purpose immediately understandable. It distinguishes from siblings like 'list_libraries' (read) and 'add_to_library' (modify existing). However, it doesn't explicitly differentiate from potential overlapping tools like 'organize_papers' or 'manage_collections', which slightly reduces specificity.

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

  Usage Guidelines3/5

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

  The description provides implied usage context ('useful for organizing papers by topic, project, or reading status'), suggesting when this tool might be appropriate. However, it lacks explicit guidance on when to use this versus alternatives (e.g., 'list_libraries' for viewing, 'add_to_library' for modifying), and doesn't mention prerequisites like authentication or permissions.

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

• get_author_metricsB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what metrics are returned but doesn't mention critical behavioral aspects like whether this is a read-only operation, potential rate limits, authentication requirements, error conditions, or data freshness. For a tool with no annotations, this leaves significant gaps in understanding how it behaves.

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

  Conciseness4/5

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

  The description is appropriately concise with two sentences. The first sentence clearly states the purpose and key metrics, while the second provides usage context. There's no unnecessary repetition or fluff, though it could be slightly more structured by explicitly separating purpose from guidelines.

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

  Completeness3/5

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

  Given that there are no annotations and no output schema, the description is moderately complete for a simple query tool. It explains what metrics are retrieved and provides usage context, but it doesn't describe the return format, error handling, or other behavioral details that would be important for an AI agent to use it correctly. The lack of output schema means the description should ideally cover return values, which it doesn't.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents both parameters ('author' and 'years') with descriptions. The description doesn't add any parameter-specific information beyond what's in the schema. According to the rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in the description.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: 'Get comprehensive metrics for an author including h-index, total citations, paper count, and citation statistics.' It specifies the verb ('Get') and resource ('metrics for an author') with concrete examples of metrics. However, it doesn't explicitly differentiate from sibling tools like 'get_author_papers' or 'get_paper_metrics', which is why it doesn't achieve a perfect score.

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

  Usage Guidelines3/5

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

  The description provides implied usage guidance: 'Useful for CV preparation and tracking research impact.' This gives context about when to use the tool but doesn't explicitly state when not to use it or mention alternatives like 'get_author_papers' for different data. It lacks clear exclusions or comparisons to sibling tools.

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

• list_librariesB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does ('List all your personal paper libraries') and output details, but lacks critical behavioral traits: it doesn't specify if authentication is required, mention rate limits, describe pagination or sorting for large result sets, or clarify what 'your personal' means (e.g., user-specific vs. shared libraries). For a read operation with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that front-loads the core action ('List all your personal paper libraries/collections in ADS') and adds valuable output details ('Shows library names, descriptions, and paper counts'). There is zero waste—every word contributes to understanding the tool's purpose and output.

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

  Completeness3/5

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

  Given the tool's low complexity (0 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the basic purpose and output format, which is sufficient for a simple list operation. However, without annotations or output schema, it should ideally mention authentication needs or behavioral constraints (e.g., is this a read-only, safe operation?). The description meets minimum viability but misses contextual details that would enhance agent understanding.

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

  Parameters4/5

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

  The input schema has 0 parameters with 100% coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, which is appropriate here—it doesn't need to compensate for missing schema details. Baseline is 4 for 0 parameters, as the description correctly focuses on output semantics without redundant input explanations.

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

  Purpose4/5

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

  The description clearly states the verb ('List') and resource ('personal paper libraries/collections in ADS'), with specific output details ('library names, descriptions, and paper counts'). It distinguishes from siblings like 'get_library_papers' (which retrieves papers within a library) by focusing on library metadata rather than contents. However, it doesn't explicitly contrast with all siblings (e.g., 'create_library' is clearly different, but differentiation from 'export_bibtex' or 'search_papers' is implied rather than stated).

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., authentication), compare it to similar tools like 'get_library_papers' for accessing library contents, or indicate scenarios where listing libraries is appropriate (e.g., before selecting one for operations). Usage is implied by the action but not explicitly defined.

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

• export_bibtexB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool is for 'exporting' and 'useful for adding references,' but does not disclose key traits such as whether this is a read-only operation, if it requires authentication, rate limits, or what the output format looks like (e.g., BibTeX string, file). This leaves gaps in understanding the tool's behavior.

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

  Conciseness5/5

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

  The description is appropriately sized and front-loaded: two concise sentences that directly state the purpose and usage context without unnecessary details. Every sentence earns its place by providing essential information efficiently.

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

  Completeness3/5

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

  Given the tool's moderate complexity (export function with one parameter) and no annotations or output schema, the description is partially complete. It covers the basic purpose and a usage hint but lacks details on behavioral traits and output format. This is adequate for a simple tool but has clear gaps in transparency and completeness.

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

  Parameters3/5

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

  The input schema has 100% description coverage, with the 'bibcodes' parameter fully documented in the schema. The description does not add any parameter-specific details beyond what the schema provides (e.g., it doesn't explain bibcode format or constraints). According to the rules, with high schema coverage, the baseline is 3 even without extra param info in the description.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: 'Export BibTeX citations for one or more papers.' It specifies the verb ('export'), resource ('BibTeX citations'), and scope ('one or more papers'). However, it does not explicitly differentiate from sibling tools like 'get_paper_details' or 'search_papers', which might also handle paper data but in different formats or contexts.

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

  Usage Guidelines3/5

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

  The description provides some usage context: 'Useful for adding references to LaTeX/Quarto documents.' This implies when to use the tool (for document citation needs) but does not specify when not to use it or name alternatives among sibling tools. For example, it doesn't clarify if this is for formatted citations vs. raw data from other tools.

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

• get_paper_metricsB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool retrieves metrics but doesn't specify whether it's a read-only operation, requires authentication, has rate limits, or what the output format looks like. For a tool with no annotation coverage, this leaves significant behavioral gaps.

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

  Conciseness5/5

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

  The description is concise and well-structured, consisting of two sentences that efficiently convey the tool's purpose and usage context without unnecessary details. Every sentence adds value, making it easy to understand quickly.

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

  Completeness3/5

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

  Given the tool has no annotations, no output schema, and a simple single parameter with full schema coverage, the description provides basic purpose and usage but lacks details on behavioral aspects like output format or operational constraints. It's minimally adequate but could be more complete for a metrics retrieval tool.

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

  Parameters3/5

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

  The input schema has 100% description coverage, with the 'bibcodes' parameter fully documented in the schema. The description doesn't add any parameter-specific details beyond what's in the schema, such as format examples or constraints. Baseline score of 3 is appropriate since the schema handles the parameter documentation adequately.

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

  Purpose4/5

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

  The description clearly states the tool's purpose with a specific verb ('Get') and resource ('detailed metrics for specific papers'), listing key metrics like citation count, reference count, reads, and citation history. It distinguishes from siblings like get_paper_details by focusing on metrics rather than general paper information, but doesn't explicitly compare to get_author_metrics or other siblings.

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

  Usage Guidelines3/5

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

  The description provides implied usage context by stating it's 'useful for tracking paper impact over time,' which suggests when to use it. However, it lacks explicit guidance on when to choose this tool over alternatives like get_paper_details or get_author_metrics, and doesn't mention any prerequisites or exclusions.

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

• search_papersA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool returns (bibcodes, titles, authors, years, citation counts) and provides query format examples, which adds useful context. However, it doesn't mention potential limitations like rate limits, authentication needs, or error conditions that would be important for a search tool.

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

  Conciseness5/5

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

  The description is appropriately sized and front-loaded: the first sentence states the core purpose, the second explains what's returned, and the third provides usage guidance with examples. Every sentence earns its place with no wasted words, making it efficient and easy to parse.

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

  Completeness4/5

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

  Given the tool's moderate complexity (search with 3 parameters), no annotations, and no output schema, the description does a good job covering the essentials: purpose, return values, and usage examples. However, it could be more complete by mentioning output format details or potential constraints since there's no output schema to document the response structure.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds some value by providing query examples ('stellar populations', 'author:Coelho', 'year:2020-2024') that illustrate parameter usage, but doesn't add significant semantic information beyond what's in the schema descriptions. This meets the baseline for high schema coverage.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with specific verb ('Search') and resource ('NASA ADS for astronomy/astrophysics papers'), and distinguishes it from siblings like 'get_paper_details' or 'get_author_papers' by focusing on search functionality. It specifies the scope (astronomy/astrophysics) and what information is returned (bibcodes, titles, authors, years, citation counts).

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

  Usage Guidelines4/5

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

  The description provides clear context on when to use this tool by explaining it handles 'natural language queries or specific field searches' and gives examples like 'stellar populations', 'author:Coelho', 'year:2020-2024'. However, it doesn't explicitly state when not to use it or name specific alternatives among siblings (e.g., 'get_author_papers' for author-specific queries).

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