知一刻 Zhiyike

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

It goes far beyond basic retrieval by detailing the internal content structure (summary, changes, deep content, observations), the output format (Markdown), and specific fallback behaviors for cover images.

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

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

The description is concise while managing a high density of information regarding content fields, formatting, and external dependencies.

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?

Since there is no output schema, the description provides excellent completeness by detailing exactly what information the AI can expect to receive and how that information will be rendered.

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 compensate. It merely states the parameter is an ID from list_news without providing any semantic explanation or constraints beyond what is already defined in the schema.

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

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

The description clearly defines the action (retrieving detail) and the resource (article content), distinguishing itself from sibling tools like list_news by focusing on the full content rather than just listing.

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 establishes a workflow dependency, requiring the ID to be sourced from list_news, which prevents incorrect invocation.

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?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real value: the date-omitted default, that the date is the publish day while contentDate is the previous day's news, pagination support, and that image blocks suppress structuredContent. It stops short of describing limits, error cases, or rate behavior, so a 3 fits given the 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.

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

Dense but front-loaded: the read action and the date-omitted default come first, then format details. Parenthetical asides (不一定是今天, 见 contentDate, 有 image 时省略 structuredContent) are information-bearing rather than filler, though the single run-on sentence is harder to scan.

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?

There is no output schema, and the description compensates well by describing the return payload: paginated items, text as formatted Markdown with cover-image syntax, thumbnail image blocks for early covered entries, and structuredContent being omitted when image is present. Only pagination defaults and error behavior remain unclear.

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 carry the load. It documents date thoroughly (YYYY-MM-DD publish/issue date for daily, YYYY-Www for weekly) and ties period to daily vs weekly via the 日报/周报 framing, but limit and offset get only a bare '支持分页' with no defaults or interaction explained.

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: read a specified issue (指定一期) from a catalog, with daily/weekly period semantics. It does not name the sibling list_reports or get_news_detail, so the boundary between fetching one issue and listing issues is left to inference, but the core action is unambiguous.

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 explains the key default (omit date → latest published issue, not necessarily today), which implicitly guides usage. However, it never says when to prefer this over list_reports or get_news_detail, nor whether listing issues first is a prerequisite, so selection guidance is only implied.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context beyond them: the data is a stored snapshot, not a live crawl, and each response carries the snapshot update time so the agent can judge staleness.

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 front-loaded sentence that states what is returned, the freshness caveat, and the snapshot timestamp. Nothing is padded and the most important constraint (not real-time) lands immediately.

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 small three-parameter read tool with no output schema, this covers the essentials — return content and freshness are stated. But with no schema descriptions and no output schema, the agent still lacks any explanation of the limit/offset pagination semantics, which is a real 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%, so the description carries the burden, yet it only maps the period concept to 'daily or weekly' and says nothing about limit or offset. Pagination range and default behavior for the two undocumented parameters are left entirely for the agent to guess.

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 names a specific verb and resource: it returns the saved AI project daily or weekly ranking plus the snapshot update time. It clearly distinguishes this from a live-scrape tool, though it never references the sibling tools (list_news, list_reports, search_library), so the agent must infer the boundary from the resource name alone.

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 'use this when...' or 'use X instead' guidance relative to the siblings. The usage is implied by the resource (fetch the trending list) and by the caveat that data is cached rather than live, which tells the agent what to expect but not when to prefer another tool.

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

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

The description provides highly valuable technical and behavioral traits beyond the annotations. It details specific content formats (Markdown, cover URLs, structured image blocks) and logic (when an image block replaces structured content), giving the AI deep context on the expected result.

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 single paragraph is dense but logically structured: first stating the core function, then describing content structure, and finally explaining operational logic (pagination). Every sentence adds specific functional detail.

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

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

Given that there is no output schema provided, the description is exceptionally complete. It explains the structure of the data, including the specific format of text (Markdown) and the mechanism for retrieving subsequent pages ('nextOffset').

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?

Since the schema description coverage is 0%, the description does a good job of contextualizing the parameters. It explains that the 'date' is part of a set of 'availableDates' and how the output handles the offset via 'nextOffset', adding semantic meaning beyond the basic schema definitions.

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 tool clearly states its purpose: querying public news by date and keyword. It distinguishes itself from sibling tools like get_report by defining its scope as 'public news' rather than reports.

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 defines crucial default behavior (today's date, newest first sort). It also explains the pagination mechanism using 'nextOffset' to guide when the agent should continue querying. It lacks explicit 'when to avoid' guidance, but its description is very clear on how it functions.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two genuinely new facts: only published reports are returned, and results are ordered newest-first. It says nothing about how limit/offset interact with that ordering or whether there is a total count.

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 sentence with no filler, front-loading the resource and the period options before the ordering note. Nothing is padded, though there is also nothing beyond that one clause.

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 read-only list tool with a complete annotation set and no output schema, the description covers the essentials of what is listed and in what order. It still leaves the agent guessing about the return shape (report titles? dates? identifiers?) and about pagination behavior across limit/offset.

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 carry parameter meaning. It only restates the period enum values ('daily'/'weekly'), which the schema already enforces, and never touches limit or offset — no defaults, no max-page guidance, no indication of the ordering they page over.

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 ('列出已发布日报 daily 或周报 weekly') and adds the ordering ('从最新一期开始'), so an agent knows exactly what it returns. It does not, however, distinguish itself from the sibling get_report beyond the implied list-vs-detail 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?

The word '已发布' (published only) and the 'directory/catalog' framing imply this is the enumeration entry point, with get_report as the detail lookup, but that routing is never stated. There are no explicit when-to-use or when-not-to-use conditions.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine context beyond that: it scopes results to published/settled items and excludes pending-review material, and it names the return fields (definition, description, source). It omits pagination behavior, which limit/offset imply.

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 dense sentence with no filler: scope first, then filtering capability, then return contents, then the exclusion rule. Every clause adds information an agent needs and the most important constraint is front-loaded.

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

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

With no output schema, the description usefully describes the return contents (definition, description, source) and the exclusion of unvetted material. The remaining gap is pagination/limit behavior for a 4-parameter tool, which is minor but not fully 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?

Schema description coverage is 0%, so the description carries the explanatory burden. It covers the filtering param (name/keyword) and implicitly the 'kind' enum (products vs concepts), but says nothing about limit or offset semantics, leaving half the parameters documented only by their bare JSON types and bounds.

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 uses a specific verb '查询' (query) and names the two resources ('已公开产品' and '已沉淀概念'), so the agent knows exactly what corpus is searched. It does not explicitly contrast with sibling tools (get_news_detail, list_reports), but those clearly cover different resources, so differentiation is implicit 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.

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

The phrase '不包含待复核资料' implicitly tells the agent this tool is for published, vetted content only, and '可按名称或关键词筛选' indicates how to narrow scope. There is no explicit statement of when to use this instead of siblings, nor any prerequisite guidance, so usage is only implied.

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