BusyBee — Social Media Data

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

No annotations exist, so the description carries the full behavioral burden. It discloses the cognitive return content (account information plus balance) and the currency unit, which is useful. It says nothing about cost of the call, rate limits, authentication prerequisites, or how the balance is presented, leaving meaningful gaps for an unannotated 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?

Two short sentences, front-loaded with what the tool returns and followed by actionable timing advice. Every sentence earns its place with 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?

For a zero-parameter read with no output schema, the description covers who the data belongs to, what it contains, and the unit of the balance. Only the shape of the returned object is left vague, a minor gap given the tool's simplicity.

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 tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly introduces no parameter concepts that would confuse the caller.

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?

States a specific verb and resource: reads the current API Key's account info and balance, denominated in USD. The scope ('current API Key') is precise enough that an agent knows exactly whose balance is returned. It doesn't explicitly differentiate from siblings, though none of them (search/get content tools) overlap in purpose.

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?

Gives clear usage context: call it before running other work to avoid exhausting the balance mid-task. That is a real 'when to use' signal rather than none. It stops short of naming alternatives or stating exclusions, which are unnecessary here since no sibling overlaps.

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 the burden. It usefully discloses the sample-then-aggregate-locally pipeline and the returned metrics, but omits read-only confirmation, permissions, cost, or rate-limit context for the underlying pull.

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

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

Two compact sentences, front-loaded with purpose and outputs. Efficient, though the closing comparative clause could be merged tighter.

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?

Good coverage of what is returned (the main value for a tool lacking an output schema), but the incomplete parameter semantics leave an agent unsure how to supply post_id/platform 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 only implicitly hints at the 'sample' parameter ('拉样本评论'); it says nothing about the format/meaning of post_id or platform (required params), leaving them undocumented anywhere.

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?

States a specific verb (aggregate insights) plus concrete output artifacts — sentiment distribution, question ratio, high-frequency words, top-liked comments. It explicitly contrasts with raw comments (the get_comments sibling), so an agent can differentiate without opening the schema.

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?

Clearly frames when to prefer this over raw comments ('more suitable for answering what users are actually saying'), giving comparative context. It stops short of explicit exclusions or naming the alternative by tool name, so not a 5.

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 the full burden; it does disclose that results are read-only raw comments with unified fields, which is real added value. It says nothing about pagination behavior despite a limit parameter, ordering of results, or what happens when a post has no comments.

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

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

Two short sentences with zero filler: the fetch purpose and output fields come first, the follow-up routing second. Nothing to cut.

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?

It covers output fields and next-step workflow, but for a 3-parameter tool with 0% schema coverage, no annotations, and no output schema, gaps remain around platform value space, limit/pagination semantics, and error behavior for a missing post.

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% and the description only implies post_id via "某条内容"; platform and limit are never mentioned. No hint about valid platform values (a list_platforms sibling exists) or what limit controls, so the agent must guess at two of three parameters.

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?

Names a specific verb+resource: fetching the comment list for a given piece of content, and adds that fields are normalized (commenter, content, likes, time). That implicitly separates it from the sibling get_comment_insights, which produces conclusions rather than raw comments, though it never explicitly says it is the raw-fetch counterpart.

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?

"拿到评论后用 get_comment_insights 出结论" gives an explicit downstream alternative and the condition that selects it, which is genuinely useful routing. It stops short of stating when not to use this tool or any prerequisites (e.g. needing a valid post_id from search_posts).

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 burden. '查…详情' clearly implies a read-only lookup, but nothing is said about permission requirements, rate limits, or what happens when the handle/id is not found.

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

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

Two short sentences with zero waste; the resource and returned fields come first and the parameter format note follows. Everything earns its place.

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 two-parameter read tool with no output schema, this is nearly sufficient: it covers what is returned and the creator identifier format. The only real gap is the enumeration of valid 'platform' values, which an agent could source from the list_platforms sibling.

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 does well for 'creator' (handle without @, or platform id) but leaves 'platform' completely unexplained — no accepted values and no enum in the schema to fall back on.

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?

States a specific verb and resource ('查单个账号的详情') and even enumerates the returned fields (粉丝数、简介、作品数), which makes the single-account scope clear. It does not explicitly name the sibling it contrasts with (search_creators), so it falls short of full sibling differentiation.

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 phrase '单个账号' implies this is for a known account rather than discovery, which hints at the search_creators alternative, but no alternative is named and no when-not-to-use condition is given. Usage is inferable rather than stated.

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?

As no annotations are present, the description carries the full burden of transparency. It provides behavioral context by clarifying that the post_id is flexible (content ID vs. video link number), which is a key operational constraint for the caller.

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 definition is extremely concise. It front-loads the main function and follows immediately with a parenthetical clarification detailing input variations, making it highly 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?

For a basic GET request tool, the description is sufficiently complete. It provides the required action and the necessary constraints for the key parameters, allowing an agent to invoke it successfully without further information.

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 must add substantial value. It achieves this by explicitly defining that the post_id can be sourced from two distinct formats: a platform ID or a numerical ID from a video link, which is not reflected in the simple 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 purpose is to 'check the details of a single piece of content.' By specifying 'single piece of content,' it effectively distinguishes this tool from broader search or listing siblings like search_posts or list_creator_posts.

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 crucial input guidelines by stating that the post_id can be either a platform's content ID or a numerical ID extracted from a video link. This operational detail helps the agent determine the appropriate input format.

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 does disclose a genuine behavioral constraint — only Douyin is supported today — which is valuable. But it says nothing about rate limits, whether results are cached/sampled, ordering, or how many items come back.

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

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

Two short sentences, capability first and use case second, with no filler. Nothing to trim and nothing buried.

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?

This is a simple read with zero required params and no output schema, so the burden is light. Still, an agent gets no hint of the return shape (a ranked list of hot topics?) or size, and no guidance beyond the single platform constraint.

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. '目前支持抖音' partially clarifies the platform parameter's only valid value, but the limit parameter (default 20) and its bounds are entirely undocumented, leaving half the surface unexplained.

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?

States a specific verb+resource: fetch platform trending/hot lists (拉平台热搜/热榜). It also scopes availability ('目前支持抖音'), which no sibling shares. It does not explicitly name sibling tools, but the resource is distinct enough from search_posts/get_comments that confusion is unlikely.

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 phrase '适合做选题和热点追踪' gives an implied usage context (content ideation, trend tracking) but no concrete when-to-use/when-not guidance and no alternative tools are referenced, e.g. list_platforms for discovering supported platforms.

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 disclosure burden. It conveys only that results are 'recently published' posts; nothing about ordering, pagination behavior, rate limits, or error behavior for an unknown creator is stated.

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

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

Two short sentences with the core purpose front-loaded and the identifier note immediately after. No filler, though the brevity contributes to the specification gaps rather than offsetting them.

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?

With no annotations, no output schema, and 0% schema description coverage across three parameters, this description is too thin for the tool's surface. An agent still cannot determine valid platform values, page-size semantics, or what the returned list looks like.

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 document all three parameters. It usefully resolves the main ambiguity for 'creator' (handle or platform id), but leaves 'platform' with no indication of accepted values and 'limit' with no mention of its default of 20 or any cap.

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?

States a specific verb and resource: listing an account's recently published posts, with the creator identifier clarified as handle or platform id. It is distinguishable from get_creator/get_post, but it never contrasts itself with the sibling search_posts, so the boundary is left implicit.

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 — call this when you already know a creator and want their recent output. There is no explicit statement of when to prefer this over search_posts, or that search_creators/get_creator should be used first to resolve a handle or platform id.

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 behavioral burden. It discloses that the tool returns platform lists, supported operations, and selection guidance, and that it should be used first. However, it does not explicitly state that it is read-only or mention authentication, side effects, or response shape.

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

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

Two short sentences with no wasted words. The purpose is front-loaded, and the first-use instruction follows directly as actionable guidance.

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 zero-parameter discovery tool with no output schema and no annotations, the description sufficiently explains what the tool returns and when to call it. It could be slightly more complete by explicitly confirming read-only behavior, but the core agent needs are covered.

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 tool has zero parameters, so there are no parameter semantics to explain. The baseline for a parameterless tool is 4, and the description does not need to compensate for missing schema details.

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 gives a specific verb and resource: list available platforms. It also states the payload includes supported operations per platform and selection guidance, which is more than a tautology. It does not explicitly contrast itself with any sibling, so it stops short of a 5.

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?

It explicitly says to call this first when using the toolset for the first time, which is clear onboarding guidance. It does not describe when not to use it or name alternative tools, but for a zero-parameter discovery tool those alternatives are not obvious among the siblings.

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 at all, the description carries the full behavioral burden. It usefully discloses the return fields (id, handle, nickname, follower count, bio), but says nothing about auth needs, rate limits, pagination behavior of limit, or how keyword matching works (exact vs. fuzzy).

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

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

Two short sentences, front-loaded with the action and followed by the payoff and the next step. Every clause earns its place, with no filler.

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

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

The description compensates for the missing output schema by enumerating returned fields, which is the single biggest gap closed. However, for a tool whose schema is entirely undocumented, leaving platform values and limit semantics unexplained keeps it from being complete enough to call confidently.

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 for three undocumented parameters. It only implies the meaning of keyword via 'search by keyword'; platform (required) and limit (default 10) get no explanation at all, and no valid platform values are given despite a list_platforms sibling existing.

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?

States a specific verb and resource in Chinese: search social-media accounts/influencers by keyword, which is clearly distinct from get_creator and list_creator_posts. It does not address the search_posts sibling, so an agent must still infer that this tool searches accounts rather than content, but the resource noun largely resolves that.

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 routes the workflow: search first, then take the handle or id into get_creator / list_creator_posts for depth. That is real when-to-use guidance with named alternatives, though it gives no exclusion for search_posts and no prerequisites or failure cases.

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 the full burden; it does disclose the result shape (author, text, time, likes/comments/plays) which is genuinely useful. It says nothing about pagination behavior of the default limit of 20, result caps, or rate limits, so an agent cannot tell how complete a result set is.

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

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

Two short sentences, front-loaded with the action and return shape, with the use case appended. Compact and waste-free, though it spends words on field enumeration while omitting the required platform parameter.

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 3-parameter, no-output-schema tool it covers the return fields well, but the required platform parameter is left unexplained and there is no routing guidance among several similar search siblings. Missing platform semantics is the clearest completeness gap.

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

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

Schema description coverage is 0% across 3 parameters, yet the description only mentions the keyword. The required 'platform' parameter has no stated meaning or valid values despite a list_platforms sibling, and 'limit' is never explained, leaving half the parameter surface undocumented in both schema and description.

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

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

States a specific verb (搜索) and resource (内容/帖子与视频), and enumerates the unified return fields, so the agent knows exactly what comes back. It does not explicitly distinguish itself from the sibling get_trending, which the 'what's hot on a topic' framing partly overlaps with.

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?

Gives one usage scenario ("适合 某个话题最近在火什么"), which implies keyword-driven topic discovery, but never says when to prefer get_trending, search_creators, or list_creator_posts instead. No exclusions or prerequisites are stated.

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