好片分享排行榜

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 usefully reveals a non-obvious behavioral trait — the ranking formula (likes×3 + comments×2 + views÷10) — but says nothing about default limit, sort/ordering guarantees, pagination, or result 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?

Three short sentences, no filler, with the core purpose front-loaded before the period glossary and formula. The formula sentence is arguably optional but adds real value for interpreting results.

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 4-param, zero-annotation, no-output-schema tool, the description covers purpose, periods, platforms and scoring but omits default limit, whether category and platform compose, and what the returned entries look like. Adequate but with clear gaps.

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

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

Schema description coverage is 0%, so the description must compensate. It fully explains the period enum values (day/week/month/year) and names the platforms, but leaves limit (no stated default or behavior) and category (14 enum values with no explanation of semantics) 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 clear verb+resource (retrieve rankings of popular videos and posts) and enumerates the covered platforms (YouTube, Instagram, Facebook, X, TikTok, Threads). It does not, however, distinguish itself from the share-oriented siblings (get_share, get_share_stats, list_new_shares, search_shares), so an agent must infer that this is the aggregate ranking view rather than a per-share lookup.

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?

There is no explicit statement of when to use this tool versus the four sibling tools, and no exclusions or prerequisites. The period glossary hints at intended use but is parameter documentation, not usage routing.

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 behavioral burden, and it does disclose the response content (share details plus comments), which is genuinely useful given there is no output schema. However, it says nothing about required permissions, whether comments are included only when present, pagination of comments, or behavior on an invalid/deleted share id.

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?

A single short clause with no wasted words and the resource named up front. It is efficient, though arguably terse to the point of under-specification rather than maximally informative conciseness.

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 one-parameter read tool with no output schema and no annotations, the description covers the 'what' adequately but leaves the parameter's meaning and the error/edge behavior unspecified. An agent could call it, but only by guessing the id semantics.

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 there is exactly one required parameter, 'id', which the description never explains — not its format, whether it is a share token/slug/numeric id, nor where to obtain it. The description therefore fails to compensate for the schema gap.

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

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

The description states a specific verb and resource ('取得一則分享') and adds scope detail ('詳細資料與留言'), so an agent knows it returns a single share's details plus its comments. It is distinguishable from list_new_shares and search_shares by the singular '一則', but it never explicitly contrasts itself with get_share_stats, which is the closest-looking sibling.

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?

There is no guidance on when to use this tool versus get_share_stats, search_shares, or list_new_shares, and no stated prerequisites (e.g., needing the share id from a search or listing call). The singular phrasing only weakly implies 'use when you already have one share id', which the agent must infer.

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 behavioral burden. It names the returned metrics but says nothing about auth requirements, whether the data is live or cached, what time window it covers, or whether it is scoped to the caller's account.

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?

One sentence, front-loaded with the verb and resource, with zero filler. Every listed metric earns its place as the substance of the answer.

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 output schema and no annotations, the description is the only source of return-value information, and it only lists metric names without shape, units, time range, or breakdown structure. It is minimally adequate for a no-arg aggregate tool but leaves real gaps.

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

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

The tool takes zero parameters, so the baseline of 4 applies. There is nothing for the description to disambiguate, and the schema is trivially complete.

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 (取得) and enumerates the exact metrics returned: site-wide share count, member count, push count, and per-platform distribution. This clearly separates it from siblings like get_share or list_new_shares, though it never names an alternative explicitly.

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

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

No guidance on when to use this tool versus get_share, get_rankings, or search_shares. The agent must infer that this is the aggregate/summary endpoint from the metric list alone.

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 behavioral burden. It conveys only ordering-by-recency and reveals nothing about pagination, defaults for limit, required auth, or result volume for a list endpoint that can return up to 100 items.

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?

A single short sentence with the core noun and the recency qualifier front-loaded; nothing is wasted. It is arguably under-specified rather than overly verbose, but structurally it is 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 listing tool with three parameters, no annotations, and no output schema, the description omits everything an agent needs beyond the bare purpose: ordering guarantees, pagination, filter semantics, and result shape. It is not sufficient to call the tool correctly without trial and error.

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 and it does not – limit, category, and platform are never explained. The two enum parameters are somewhat self-documenting through their allowed values, but there is no statement about defaults, combination behavior, or what an omitted filter means.

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 states a specific verb-resource pair ("列出最新分享的影片與貼文" – list the latest shared videos and posts) and the word 最新 signals a recency-ordered listing. It is clear what the tool returns, but it never distinguishes itself from sibling search_shares or get_rankings, so an agent must infer the split.

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?

There is no when-to-use guidance, no exclusions, and no mention of the alternatives (search_shares for filtered lookups, get_rankings for ranked ordering). The agent is left to guess whether this is the right tool versus a sibling.

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 exist, so the description carries the full burden. It does add real behavioral context by disclosing which fields are matched (title, description, original author), but says nothing about result ordering, limits, pagination, or auth, which matter for a search endpoint.

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?

One compact sentence with zero filler, and the core action is front-loaded. It is arguably too terse rather than verbose, so length is not a problem here.

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 one-parameter search tool with no output schema, the description covers the essentials of what is searched and how. It stops short of explaining result behavior or limits, leaving an agent to guess at what a response 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% for the single 'query' parameter, so the description must compensate. It clarifies that the argument is a keyword string applied against titles, descriptions and authors, which is genuinely useful, but adds no syntax, matching-rule, or format detail.

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 (搜尋) and resource (網友分享的影片與貼文), and narrows the scope by naming the searched fields (標題、說明、原作者). It is distinguishable from siblings like get_share (single share) and list_new_shares (browsing), though it never names them explicitly.

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

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

The phrase 用關鍵字搜尋 implies this is the tool for keyword-based lookup, which is usable context, but there is no explicit when/when-not guidance or comparison to list_new_shares or get_rankings. Usage must be inferred from the name and sibling set.

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