kebiao 课标

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful context beyond that: it says the response contains change highlights, the revised original text, and newly inserted wording, which matters because there is no output schema. It does not cover error behavior or what happens for standards without a 2025 revision.

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 core purpose is front-loaded and the two sentences are short and free of filler. The bilingual duplication (Chinese followed by an English restatement) is mildly redundant for an agent, but it costs little and does not obscure the content.

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-only tool with one fully documented parameter and complete annotations, and the description goes further by describing what the response contains in the absence of an output schema. The only real gap is the lack of guidance on when to choose this over get_standard, which is minor for a tool this simple.

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?

There is a single parameter, code, and the schema description coverage is 100%, so the schema already explains it as a standard or key-point code. The description adds no further meaning, such as format, example values, or how the code relates to the codes used by get_standard. Baseline 3 applies when the schema does the heavy lifting.

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

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

The description gives a specific verb and resource: it lists what the 2025 revision changed in a standard, including change points, revised text, and newly written wording. That is clearly different from the sibling tools get_standard and list_standards, but the description never names those alternatives explicitly, so the distinction has to be inferred.

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 only implied: an agent can infer it should call this when it wants a diff rather than the full text, but there is no explicit when-to-use statement, no mention of when to prefer get_standard or search_standards, and no prerequisites such as requiring a standard that actually has a 2025 revision.

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 read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful behavior context beyond that: results are ordered as AI-read judgments with textbook quotations and page numbers first, then machine-aligned entries, plus the subject/grade filtering capability.

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 output structure and the use case are front-loaded and every sentence carries information. The trailing English sentence is a bilingual restatement rather than new content, which is minor padding but not harmful.

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 explaining the two-tier result format and ordering. It does not say what happens when a title matches nothing or how many matches are returned, which is a small remaining gap for a lookup tool.

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 100%, so the baseline is 3, and the description does add value by giving example query titles (「分数的基本性质」「七七事变与全民族抗战」) that show what a well-formed query string looks like. Grade and subject are only mentioned as filters, without format guidance, but the schema already covers those.

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: given a textbook unit/chapter/lesson title, return its corresponding curriculum-standard points. It also spells out the two-part result (AI per-lesson reading of the textbook text, then machine table-of-contents alignment), which lets an agent distinguish this textbook-to-standard lookup from standard-oriented siblings like get_standard or search_standards.

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 gives a concrete usage scenario (「下周教这一课，对应哪条课标」) and states that results can be filtered by subject and grade, so the when-to-use case is clear. It does not explicitly name an alternative tool or a when-not-to-use case, which keeps it short of 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: what each returned question contains (misconception explanation, how to respond in class, correct method, graded practice) and that it is directly projectable. It does not mention the default/max limit behavior, which is left to the schema, keeping it below 5.

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 front-loaded purpose is good, but the parenthetical enumeration of 13 subjects is long and low-value, and the trailing English sentence ('Whole-class diagnostic questions with misconception-tagged wrong answers, every subject') duplicates what the Chinese text already said. The mixed-language restatement costs space without adding information.

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, so the description carries the burden of explaining returns, and it does so well by describing the question payload (misconception tagging, corrective approach, three-tier practice). Limits/pagination are omitted but are covered by the schema. Complete enough for an agent to invoke correctly without surprises.

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 100%, so the schema already documents code, grade, limit, topic and subject. The description's '按学科、课标要点或标准编码、年级、或关键词查' essentially restates those handles without adding syntax, format, or interaction rules beyond the schema. Baseline 3 is appropriate.

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: retrieve classroom diagnostic questions, and it richly characterizes what those are (whole-class gesture answers, each wrong answer tagged with a misconception, correct approach, three-tier practice, projector-ready). An agent can distinguish this from sibling tools like get_standard or list_standards because the resource is a ready-to-use question bank rather than standards metadata. It stops short of explicitly naming any sibling, so a 4 rather than 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 tells the agent which handles can be used to query (subject, standard code, grade, keyword), which implies how to call it, but gives no explicit when-to-use-vs-alternatives guidance and no exclusions. Nothing tells the agent when to prefer get_standard or search_standards instead, 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.

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds valuable context beyond that: the returned content is 课标原文 and may be grouped by 核心素养 or by subject. It does not mention empty results or error behavior, keeping it short of a 5.

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 front-loaded with the core action and scope before the exclusions. Every Chinese clause earns its place; the trailing English gloss 'Stage goals of a subject.' is redundant padding but minor.

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 must convey what comes back, and it does so only loosely ('课标原文, 按核心素养或学科分组'). That is enough to set expectations but leaves the response shape and verbosity vague for a tool with no output schema.

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 100%, so the baseline is 3. The description goes beyond the schema by explaining that stage means 水平 for 体育 and that some subjects have only a single stage, which meaningfully shapes how the optional stage parameter should be populated.

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 pairs the specific verb 查看 with the precise resource 学段目标, and notes the subject-specific variation (体育 uses 水平目标). It also explicitly distinguishes itself from list_standards, so an agent can choose it without opening the sibling's 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?

It gives explicit routing rules: for 语文/英语 学段要求/学段目标, use list_standards instead, and it flags the edge case that the five new junior-high subjects have only one stage. When-to-use, when-not, and the alternative are all 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?

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description clears it by disclosing two behaviors annotations cannot: the response distinguishes original curriculum text from kebiao-composed text, and a legacy 2022 code does not fail but reports which new standard absorbed it. It stops short of stating what happens for an unrecognized code.

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 content is front-loaded — resource, then return payload, then accepted code forms — and every clause earns its place. The cost is a single dense run-on sentence duplicated verbatim in a second language, which is useful for mixed-language agents but doubles the length without new information.

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, so the description carries the return-shape burden and does so by naming all four payload components including provenance marking and page numbers. For a one-parameter read tool this is close to complete; only the failure behavior for an unknown or malformed code is unaddressed.

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 one parameter at 100% schema coverage the baseline is 3, and the description does add value over the schema's bare "标准、要点或旧编码" by giving concrete examples of each code family. However, it still does not specify the code grammar or whether lookups are exact-match only, so the added meaning is illustrative rather than operative.

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 ("按编码查看一条课标" / "Look up one standard by code") and enumerates exactly what is returned: the standard sentence with provenance, all point originals with page numbers, academic requirements, and links. The accepted code formats (MA-S2-NA-02, point codes like MA-S2-NA-02.1, legacy MA-D2-AL-005) make it immediately distinguishable from list_standards and search_standards.

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?

"按编码查看" establishes the precondition that the agent already has a code, which implicitly separates this from the search/list siblings that produce codes. It does not explicitly say "use search_standards when you don't have a code" or name any sibling, so the routing is implied 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?

The annotations already declare readOnly, idempotent, closed-world, and non-destructive behavior, so the description does not need to repeat the safety profile. It adds real value beyond them: the results are produced by an AI that read each lesson's original text, each entry includes a quotation and page number, and when per-lesson results are missing it falls back to machine-aligned units; it also warns that everything is pending verification (都待核验). The main remaining gap is that the output shape is not described, but because no output schema exists, that gap is only partly forgivable.

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 Chinese sentence front-loads the core purpose and then adds the provenance and verification caveats efficiently. The trailing English fragment 'Textbook lessons and chapters for a standard' is a near-redundant restatement, though it is harmless. Overall it is tight, with only minor waste.

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-only lookup with no output schema, the definition is nearly complete: it explains what is returned (lessons, quotes, page numbers, fallback units) and flags data reliability. What is missing is the response structure, such as paging or result ordering, but that is a small 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?

Schema coverage is 100% for the single parameter, and the schema already defines `code` as 标准或要点编码. The description's phrase 一条标准或要点 mirrors that wording, so it adds little new meaning about acceptable code formats or how to obtain a code. With a fully documented one-parameter schema, the baseline of 3 is appropriate.

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: it returns the textbooks and lessons in which a given standard or key point (标准/要点) is taught, and it names the textbook editions (人教版, 统编版). This distinguishes it from find_textbook_chapter, which works in the opposite direction (chapter to standard). It is clear, but the direction of the relationship is stated only implicitly rather than with an explicit sibling contrast.

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 by the single required input (a standard code), so an agent can infer that it should call this tool when it has a code and wants teaching locations. However, the description never states when to prefer this over find_textbook_chapter or search_standards, and it gives no prerequisites or exclusions. The guidance is therefore adequate at best, not explicit.

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 annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered before reading the description. The description's added value is the output shape (coding, name, domain, key-point count), which matters because no output schema exists, but it says nothing about result size, ordering, or what an empty stage filter returns.

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 core scope and the get_standard routing hint are front-loaded in the first two clauses, with no filler. The trailing English sentence "List a subject's standards." largely duplicates the Chinese text and adds little for a reader who already parsed the first sentence.

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 a fully described schema and full annotation coverage, the definition covers purpose, routing, optional filter, and returned fields — enough to call it correctly. Only ordering, volume, and empty-result behavior remain unaddressed, which are minor for a listing tool.

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 100%, and both parameters carry their own descriptions including an example for subject, so the schema already does the heavy lifting. The description adds only that stage is an optional narrowing filter ("可限定一个学段"), which matches the baseline-3 case where the schema leads.

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 (list a subject's standards), names the optional scope (stage), and enumerates the returned fields (编码、名称、领域、要点条数). It also explicitly separates itself from get_standard, so an agent can pick between the overview and detail tools without opening a 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?

"适合先看全貌再用 get_standard 看细节" gives a concrete when-to-use rule and names the alternative tool, which is exactly the routing decision an agent faces here. It stops short of exclusions — it does not say when to prefer search_standards or list_subjects instead.

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, closed-world and non-destructive, so the safety profile is covered. The description adds useful substance beyond that: the fixed count of 14 subjects, the curriculum-standard edition (2022, revised 2025), and the shape of the returned summary counts. No pagination or volume concerns exist for a zero-parameter 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 sentences, front-loaded with the resource and the enumeration detail, with no filler. The bilingual duplication adds length without new information, but it is a minor cost.

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 must convey return shape, and it does at a summary level (subjects, stages, standards, key-point counts). For a simple zero-argument listing tool this is nearly complete; only the exact record structure is left unstated.

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 no parameters and the schema is a closed empty object, so there is nothing to disambiguate; the baseline for zero parameters applies. The description correctly avoids inventing parameter guidance.

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 ('List the subjects' / 列出学科) and scopes it to the 14 compulsory-education curriculum-standard subjects with version info. It also states what is returned (stages, standards, key-point counts). It does not explicitly distinguish itself from sibling list_standards, which also enumerates items, 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?

The listing of stages/standard counts implies this is an overview or entry-point tool, but it never says when to use it instead of list_standards, search_standards, or get_standard. An agent must infer the routing from the noun 'subjects' 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?

The annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds that results are ranked by relevance and include verbatim key-point excerpts plus links, and that the corpus is the 2025 revision; it stays silent on ranking behavior, empty-result handling, and coverage limits. That is solid but modest added value beyond the annotations.

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 key information (what it does, what it returns, the filters, examples) is front-loaded in two dense Chinese sentences with little waste. The trailing English sentence 'Search the standards by topic.' merely restates the opening and could be 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?

There is no output schema, and the description compensates by naming the three return components: matching standard, key-point text, and link. For a four-parameter read-only search tool this is nearly complete; the remaining gap is that it does not say how results are ordered or what happens when there are no matches.

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 100%, so the baseline is 3; the description raises it slightly by framing query as a single-sentence topic (用一句话) and by confirming that subject and stage act as filters while the query is free-text. It adds no format hints for the allowed stage values, such as 3-4/五年级/初中, beyond what the schema already gives.

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 (检索/semantic search) and resource (义务教育课程标准, 2025 修订版), and it states what comes back: the top-matching standards, the matched key-point text, and links. It does not explicitly distinguish itself from its siblings list_standards, get_standard, or find_textbook_chapter, so an agent must infer that this tool does ranked topic search rather than listing or fetching by id.

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?

Concrete example queries (「三年级科学里讲植物生长的课标」, 「初中物理 浮力」) make the intended input shape and the when-to-use context unmistakable, and the phrase 可按学科、学段筛选 signals the optional filters. There are no explicit exclusions or pointers to alternative tools for listing or fetching one standard by id.

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