Server Quality Checklist

Tool Scores

• get_user_last_tweetsB
  3.3/5.0
  Behavior2/5

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

  With no annotations provided, the description must convey behavioral details. It discloses that cursor is for pagination and that userId is more stable/faster, but omits critical traits such as rate limits, result ordering, tweet count limits, error handling, or behavior when both userId and userName are provided. This is a significant gap.

  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 well-structured with a clear purpose statement, Args list, and Returns section. Each line adds value, though the formatting could be slightly improved with bullets for readability. It avoids unnecessary fluff.

  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?

  The description covers the essential parameters and return type, but lacks edge-case behavior (e.g., what happens when both userId and userName are given, which takes precedence) and does not mention output details like number of tweets or sorting. No output schema exists, so the description should provide more context on the returned dictionary structure, which it does not.

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

  Parameters5/5

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

  The input schema has no parameter descriptions (0% coverage), but the description thoroughly explains each parameter: userId (recommended, stable, fast), userName (screen name), and cursor (for pagination, empty on first page). This fully compensates for the schema gap and adds meaningful usage guidance.

  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 retrieves a user's latest tweets, using the verb '获取' (get) and specifying the resource '用户最新的推文' (user's latest tweets). This distinguishes it from sibling tools like getUserInfo or getFollowers, though it doesn't explicitly contrast with getTweetsByIds which fetches specific tweets.

  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 explicit guidance is provided on when to use this tool versus alternatives. The description mentions parameter preferences but does not explain scenarios like 'use when you need recent tweets' or 'use instead of advanced_search for timeline data'. The only implied usage is from the tool's name, which is insufficient.

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

• get_user_info_by_usernameA
  3.5/5.0
  Behavior2/5

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

  With no annotations, the description must disclose behavioral traits but only states that it returns a dictionary with user info. It does not mention whether it's a read-only operation, error handling behavior, or any authentication requirements, leaving significant gaps for an agent.

  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, well-structured with Args and Returns sections, and front-loads the primary action. Every sentence serves a purpose with no redundant information.

  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?

  For a simple single-parameter getter, the description covers the main purpose and return type. However, given no output schema or annotations, it leaves unanswered questions about error responses and edge cases (e.g., non-existent user), making it incomplete but not severely so.

  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 description explains that the parameter is a Twitter username handle without the '@' symbol, which adds meaning beyond the bare schema definition. However, it inconsistently refers to the parameter as "username" while the schema defines it as "userName", creating potential confusion.

  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 function: "根据用户名Handle获取用户信息" (Get user info by username handle). This specific verb-noun pair distinguishes it from sibling tools like batch_get_users_by_ids and get_tweet_replies.

  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 implies the tool is for retrieving user info via a username handle, and specifies that the handle should not include '@'. However, it does not provide explicit context for when to choose this tool over alternatives (e.g., batch_get_users_by_ids for ID-based lookups).

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

• batch_get_users_by_idsA
  3.6/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden. It only says the tool returns a dictionary and provides an argument example. It does not disclose how invalid IDs are handled, whether results are partial, authentication or rate-limit requirements, or any other behavioral traits beyond the basic fetch.

  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 with Args and Returns sections. It includes an example and no irrelevant details, making it 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?

  The tool is simple, but given the absence of annotations and an output schema, the description is incomplete. It does not specify the structure of the returned dictionary, behavior on nonexistent IDs, or any guidance on when to use it versus sibling tools, leaving important gaps for an agent.

  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 schema only requires a string user_ids, but the description adds the comma-separated format and a concrete example ('1234567890,1234567891,1234567892'), which significantly clarifies how to construct the argument.

  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 function: 'batch get user information by user ID'. It identifies the specific resource (users) and the batch scope via multiple IDs, which distinguishes it from sibling get_user_info_by_username that uses a single username.

  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 implies batch usage by specifying a comma-separated list of user_ids, but it does not explicitly state when to choose this tool over alternatives or exclude scenarios where other tools are more appropriate. No comparison with siblings is provided.

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

• get_tweet_quotationsA
  3.6/5.0
  Behavior3/5

  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 discloses pagination behavior (max 20 per page) and the use of a cursor, as well as the default for includeReplies. However, it does not describe the structure of the returned dictionary or any edge cases.

  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 compact, organized into Args and Returns sections, with no redundant content. Every line serves a purpose.

  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?

  The tool has 5 parameters and no output schema, requiring the description to explain return values. It returns a dict of quotes with up to 20 per page and notes the cursor, but lacks a detailed schema of the returned object, which could be needed for full usage.

  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?

  With 0% schema description coverage, the Args section explains every parameter's meaning and defaults (e.g., tweetId, sinceTime, untilTime, includeReplies, cursor). This compensates for the schema's lack of descriptions, though details are concise.

  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 states the tool retrieves tweets that quote a specified tweet (via tweetId), and the return description confirms it returns quoted tweets. The first line is slightly ambiguous but the Args clarify the resource, and it distinguishes from sibling tools like replies or retweeters.

  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?

  No explicit alternatives or when-to-use guidance is provided. The tool's purpose is implied by its name and description, allowing an agent to infer when to use it. No exclusions or comparisons with sibling tools are given.

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

• get_tweets_by_idsA
  3.9/5.0
  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 only states the return type ('a dictionary containing a list of tweets') but gives no information on error handling, rate limits, invalid ID behavior, or pagination. This is a minimal disclosure.

  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 compact, structured with Args/Returns sections, and every sentence is useful. The purpose statement is front-loaded and the parameter example is directly relevant.

  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?

  For a simple one-parameter tool with no output schema, the description is adequate but not complete. It lacks context on edge cases (e.g., what happens if an ID is invalid or not found, maximum number of IDs allowed) and doesn't elaborate on the returned tweet structure, which would help an agent fully understand the tool's behavior.

  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?

  Schema description coverage is 0%, so the description compensates by explaining the tweet_ids parameter format: 'list of tweet IDs, multiple IDs separated by commas' with a concrete example. This goes beyond the schema's bare string type and gives the agent actionable syntax guidance.

  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 verb and resource: '通过推文ID获取推文' (get tweets by tweet IDs). This distinguishes it from sibling tools like get_user_last_tweets or get_tweet_replies, which focus on user-specific or relation-specific fetches.

  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 implies when to use this tool (when you have tweet IDs and need the corresponding tweets) and provides an example argument format. However, it doesn't explicitly exclude alternatives or state edge cases like 'do not use for user timelines', though the purpose is clear enough to infer.

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

• get_user_followersA
  3.9/5.0
  Behavior3/5

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

  Without annotations, the description discloses pagination behavior (max 200 followers per page, empty cursor for first page) and specifies that userName refers to the screen name. However, it does not mention any authentication requirements, rate limits, or error handling, leaving some behavioral uncertainty.

  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 with clear Args and Returns sections. It contains no redundant information and is appropriately sized for a two-parameter tool.

  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?

  The description covers the core usage and return shape (dictionary with up to 200 followers per page). However, it lacks more detailed output structure, error scenarios, and usage context relative to sibling tools, which would be helpful given the absence of annotations and output schema.

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

  Parameters5/5

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

  The description adds significant value beyond the schema by explaining that userName is the screen name and is required, and that cursor is for pagination with an empty string for the first page. This clarifies both parameters meaningfully given the schema provides no property descriptions.

  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 retrieves a user's followers list, and explicitly specifies the parameter 'userName' as the screen name. This distinguishes it from sibling tool get_user_followings, which retrieves the list of users a given user follows.

  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 get_user_followings. There is no mention of context, prerequisites, or exclusions. The only implicit signal is the tool name.

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

• advanced_search_tweetsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool returns a dict with about 20 tweets per page, that queryType defaults to 'Latest', and that cursor enables pagination. This is valuable behavioral context beyond the schema, though it omits potential errors, rate limits, and more detailed edge-case 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 uses a clear, structured Args/Returns format with minimal but complete detail. Every line contributes useful information, and there is no redundant or filler text. The example query adds value without bloating the description.

  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?

  For a search tool with no output schema, the description gives an overview of the return format but lacks specific fields of the returned tweets, limitations of the query syntax (only one example), and error handling behavior. The pagination and queryType details are helpful, but the tool's complexity warrants more depth to be fully complete.

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

  Parameters5/5

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

  The schema provides only types and defaults (0% schema description coverage), so the description must compensate. It explains every parameter: query with a full example, queryType with allowed values and default, and cursor with pagination semantics. This fully covers the parameter meanings and usage details.

  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 searches tweets ('高级搜索推文') and provides a concrete query example showing advanced syntax. This distinguishes it from sibling tools that are specific retrieval operations (e.g., get_user_last_tweets, get_tweets_by_ids) rather than general search.

  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 shows how to construct a query (with OR, from:, since:) and explains queryType options and cursor pagination, giving implied usage context. However, it does not explicitly state when to prefer this over alternatives or provide any exclusions, so the guidance is implicit rather than explicit.

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

• get_user_followingsA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses pagination behavior (cursor usage, first page empty) and result limit (max 200 per page), and states the return type. It does not mention error handling or authentication, but for a read-only retrieval tool, these are less critical.

  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 with a clear Args/Returns structure. Every sentence provides necessary information, and it is front-loaded with the purpose. No redundant text.

  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?

  The tool is simple, and the description covers the main aspects: what it returns (dictionary), pagination, and page size. It lacks error scenarios or rate limits, but these are not essential for a basic fetch tool. With no output schema, the return description adds necessary context.

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

  Parameters5/5

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

  Schema has 0% coverage, so description must compensate. It fully explains both parameters: userName as screen name, cursor as pagination token with first-page default. This adds meaning beyond the bare schema.

  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 it fetches the user's following list, using the verb '获取' (get) and specific resource. It distinguishes from sibling tool get_user_followers by specifying '关注列表' (following list) rather than followers.

  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 implies when to use via its purpose but does not explicitly mention alternatives or exclusions. It does not say 'use this instead of get_user_followers' or provide context for when this tool is preferred over other user-related tools.

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

• get_user_mentionsA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses key behaviors: requires a screen name, filters by unix timestamps, paginated via cursor, returns up to 20 mentions per page. It does not explicitly state read-only behavior or rate limits, but the 'get' verb and focus on retrieval imply a safe read operation. The pagination limit is important 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.

  Conciseness5/5

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

  The description is well-structured with Args and Returns sections, one line per parameter, and a clear opening statement. No filler or redundant content. It is appropriately concise while conveying all necessary information.

  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?

  The tool has 4 parameters, no output schema, and no annotations; the description covers all parameters and the pagination/return limit. However, it does not describe the structure of the returned tweet objects (e.g., fields included), which would be helpful given the absence of an output schema. Minor gap, but overall sufficient for common use.

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

  Parameters5/5

  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 fully explains every parameter: userName is a screen name and required; sinceTime and untilTime are unix timestamps (seconds) bounding the range; cursor is for pagination with an empty first-page value. This adds complete semantic meaning beyond the bare schema titles.

  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 '获取用户的提及' (get user mentions), which is a specific verb+resource. It distinguishes from sibling tools like get_user_last_tweets and get_tweet_replies by focusing on mentions, not the user's own tweets or replies to them.

  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 implies usage context (retrieving mentions of a specific user within optional time ranges and with pagination) but does not explicitly state when to choose this tool over alternatives, nor does it name any alternative tools or exclusion criteria. It provides enough to infer use case but lacks explicit guidance.

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

• get_tweet_retweetersA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full transparency burden. It discloses pagination behavior via the 'cursor' parameter, states the first page uses an empty string, and indicates the response is a dictionary with about 100 users per page. It does not mention authentication or rate limits, but for a read-only list endpoint this is reasonably transparent for an AI agent.

  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 compact and well-structured: a one-line purpose followed by concise Args and Returns sections. Every sentence provides necessary information without verbosity or repetition, 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.

  Completeness5/5

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

  The tool is simple with only two parameters, and the description covers the purpose, parameter semantics, return shape, pagination behavior, and page size. No output schema exists, so the description sufficiently compensates by stating the return type and content. There are no significant gaps for an agent to invoke this tool correctly.

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

  Parameters5/5

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

  The tool description explicitly explains both parameters: 'tweetId' is the tweet ID and 'cursor' is a pagination cursor with the first page as an empty string. This adds meaning beyond the bare schema (which lacks descriptions and only lists types/defaults), fully compensating for the 0% schema description 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 retrieves users who retweeted a tweet ('获取转发推文的用户'), specifying the resource (retweeters) and the verb (get). This distinguishes it from sibling tools like get_user_followers or get_tweet_replies, which target different relationships or content.

  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 explains the parameters and return value, implying usage when a list of retweeters is needed for a given tweet. However, it does not explicitly contrast with alternatives or state when not to use this tool, leaving adoption to inference from the tool name and description.

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

• get_list_tweetsA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden, and it delivers key behavioral detail: it returns a dictionary with a maximum of 20 tweets per page, uses a cursor for pagination, and defaults includeReplies to True. It does not mention rate limits or error handling, but for a read-only operation this is a reasonably transparent disclosure of behavior, scoring a 4.

  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 exceptionally well-structured: a one-line summary, then an Args list, then Returns. Every sentence carries useful information with no fluff. It front-loads the purpose and keeps parameter details compact, scoring a 5.

  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—5 parameters, time filters, pagination—the description covers the parameters and states the return format (dictionary with up to 20 tweets per page). However, it lacks detail on the exact output structure (tweet object fields) and edge cases like empty results or invalid list IDs, leaving a small but noticeable gap. Thus a 4.

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

  Parameters5/5

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

  The input schema has 0% description coverage, but the description fully compensates by explaining every parameter: listId, sinceTime (after Unix seconds), untilTime (before Unix seconds), includeReplies (default True), and cursor (empty string for first page). This adds essential semantics beyond the raw schema, meriting a 5.

  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 function: '获取列表中的推文' (Get tweets from a list), specifying both the action (get) and the resource (list tweets). This distinguishes it from sibling tools that operate on users or individual tweets, matching a 5: specific verb+resource, clearly differentiates from siblings.

  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 for when to use the tool: when you need tweets from a specific list, with optional time range and pagination. It gives parameter meanings and default behaviors, but does not explicitly mention alternatives or when not to use, which prevents a 5. Still, it offers enough context to decide appropriately among siblings.

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

• get_tweet_repliesA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It explains the return format (a dict containing reply tweets), pagination (cursor, first page empty, 20 replies per page), and time filters (sinceTime/untilTime as unix timestamps). It lacks details on error handling or rate limits but covers the main behavioral aspects.

  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. It starts with a clear purpose statement, then lists each argument with its semantic explanation, and ends with return information. Every sentence serves a purpose without unnecessary verbosity.

  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 complexity (pagination, time filters, specific tweetId requirement) and the absence of an output schema, the description covers the essential usage details: return type, page size, cursor usage, and time parameters. It does not detail the internal structure of each reply tweet or error scenarios, but is sufficiently complete for an agent to invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must fully compensate for parameter meaning. It does so for all four parameters: tweetId (must be original, non-reply), sinceTime/untilTime (unix timestamps in seconds), and cursor (pagination, empty string for first page). This adds significant value beyond the bare schema.

  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 function: '获取推文的回复' (get replies to a tweet). It specifies the resource (tweet) and the action (fetching replies), and distinguishes from sibling tools by emphasizing that tweetId must be the original tweet, not a reply.

  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 for when to use the tool (to fetch replies to a specific original tweet) and adds a key usage constraint: the tweetId must be an original tweet, not a reply. It does not explicitly mention alternatives or when not to use it, but the context is clear.

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