Kanji and math worksheets for kids. Review link, no login.
Score is being calculated.
作れる漢字プリントの範囲（教育漢字・漢検の級）、形式、指定した字の問題の数を返します。
| Name | Required | Description | Default |
|---|---|---|---|
| chars | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds that the tool returns information (ranges, formats, counts), but does not disclose any additional behavioral traits such as rate limits or authentication requirements.
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 a single, front-loaded sentence with no wasted words. It packs the returned information efficiently, though the parenthetical about educational kanji and kanken levels adds slight density.
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 should explain return values. It lists the main categories returned (range, format, question count), which is adequate for a simple query tool, but it lacks detail on the structure or format of those returns, leaving some gaps for the agent.
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 references '指定した字' (specified characters), which gives meaning to the single 'chars' parameter as the characters to inspect, but it does not explain that the parameter is an array, that it is optional, or that it has a max of 24 items.
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 ('返します' / returns) and resources (range of kanji worksheets, formats, question counts). It clearly identifies the tool's function as a query/check operation, but does not differentiate it from siblings like create_kanji_worksheet.
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 when-to-use guidance or named alternative. However, the tool name and description imply it is used to check available ranges before creating worksheets, which is a reasonable implied usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
既存の問題を組み合わせて A4・24マスのプリント案を作り、問題一覧（番号・種類・問題文・答え・字）と確認用の短いリンク（30日有効）を返します。形式を省くと書きと読みのテストになります。部首・画数テスト（format=test_strokes）・熟語の構成テスト（format=test_structure。1問の差し替えはできない）・対義語・類義語テスト（format=test_pairs。1問の差し替えはできない）・同音異字テスト（format=test_homophones。1問の差し替えはできない）・四字熟語テスト（format=test_yoji・意味つきは test_yoji_meaning。1問の差し替えはできない）・誤字訂正テスト（format=test_correction。4〜2級。1問の差し替えはできない）・同訓異字テスト（format=test_kun_homophones。1問の差し替えはできない）・音と訓テスト（format=test_onkun。4〜6年か7〜5級。4年・7級は1字の形。1問の差し替えはできない）・おなじなかまの漢字テスト（format=test_radical_group。2〜4年か9・8・7級。1問の差し替えはできない）・熟語の一字テスト（format=test_jukugo。5・6年か6・5級。1問の差し替えはできない）・二つの読みテスト（format=test_two_readings。1〜4年か10〜7級・準2・2級。1問の差し替えはできない）・漢字識別テスト（format=test_shikibetsu。4・3級。1問の差し替えはできない）・熟語作りテスト（format=test_tsukuri。4〜6年か7〜5級。1問の差し替えはできない）・よみがなの一字テスト（format=test_kana_blank。1・2年か10・9級）・正しいよみがなテスト（format=test_kana_choice。1年か10級。どちらも1問の差し替えはできない）・対となかまの字テスト（format=test_char_pair。1・2年か10・9級。1問の差し替えはできない）・正しい漢字テスト（format=test_kanji_choice。2年か9級。1問の差し替えはできない）も作れます。プリントの保存と PDF の作成はしません。
| Name | Required | Description | Default |
|---|---|---|---|
| chars | Yes | プリントに載せる字（重複なし）。テスト（書き・読み）は8〜24字、部首・画数テストは4〜6年相当（7〜5級）が6〜12字・ほかは12〜24字、練習は1〜6字。書き・読みのテストで25字以上・8字未満のときは、字の絞り方や分け方の案（proposals）を返す。部首・画数テスト（test_strokes）は6〜12・12〜24字の範囲外なら誤りを返すだけで、proposals は付かない。熟語の構成テスト（test_structure）と対義語・類義語テスト（test_pairs）は14字か22字、同音異字テスト（test_homophones）は8字か12字、四字熟語テスト（test_yoji）は16字か24字、意味つき（test_yoji_meaning）は8字か12字、誤字訂正テスト（test_correction）は16字か24字、同訓異字テスト（test_kun_homophones）は8字か12字、音と訓テスト（test_onkun）・おなじなかまの漢字テスト（test_radical_group）は14字か22字、熟語の一字テスト（test_jukugo）は16字か24字、二つの読みテスト（test_two_readings）は8字か12字、漢字識別テスト（test_shikibetsu）は10字か15字、熟語作りテスト（test_tsukuri）は 4年・7級が10字か15字、5年・6級が4字か6字、6年・5級が10字か15字、よみがなの一字テスト（test_kana_blank）・正しいよみがなテスト（test_kana_choice）は8字か16字、対となかまの字テスト（test_char_pair）は14字か22字、正しい漢字テスト（test_kanji_choice）は8字か16字で、それ以外は誤りを返すだけ。 | |
| grade | No | 教育漢字のプリントの学年（1〜6）。省くと字の配当学年の最大。漢検のプリントでは使わない。 | |
| title | No | 紙面のタイトル（1〜60文字）。省くと自動で付く。テストのタイトルに出題する字が入っていると、答えが見えるため受け付けない。 | |
| words | No | 優先して出題する語（例：想像・経験）。指定した字の問題に同じ語があれば先に選ぶ。 | |
| format | No | practice（練習）・test_mixed（書きと読み）・test_write（書きだけ）・test_read（読みだけ）・test_strokes（部首・画数テスト。学年か級が必要）・test_structure（熟語の構成テスト。二字熟語の組み立てを記号で答える。5・6年か6〜2級だけ。6・5級は4型、4〜2級は5型）・test_pairs（対義語・類義語テスト。熟語の空いた字を後のひらがなから選んで漢字で書く。4〜6年か7〜2級だけ。4年・7級は対義語だけ、準2・2級は熟語まるごと。字数は14字か22字）・test_homophones（同音異字テスト。同じ音読みで字の違う2問を1組にし、カタカナの読みの漢字を書く。3〜6年か8〜2級だけ。字数は8字（16問）か12字（24問）で、相手の字は自動で選ぶ）・test_yoji（四字熟語テスト。1字をカタカナにした四字熟語の、その字を漢字で書く。6年か5〜2級だけ。字数は16字か24字で、語は自動で選ぶ）・test_yoji_meaning（test_yoji に語の意味の短い文を付ける。字数は8字か12字）・test_correction（誤字訂正テスト。文の中で同じ読みの別の字にすり替えた1字を見つけ、誤字と正しい字を書く。4〜2級だけ。字数は16字か24字で、誤字は自動で選ぶ）・test_kun_homophones（同訓異字テスト。同じ訓読みで字の違う2問を1組にして漢字を書く。学年か級が必要。字数は8字か12字で、相手の字は自動で選ぶ）・test_onkun（音と訓テスト。4年・7級は漢字1字の読みが音読みか訓読みか、5・6年と6・5級は二字熟語の読みが音と音・音と訓・訓と訓・訓と音のどれかを記号で答える。4〜6年か7〜5級だけ。字数は14字か22字で、4年・7級は音読み・訓読みの読みがある字を、ほかはイ・ウ・エの語がある字を14字なら2字ずつ、22字なら3字ずつ以上入れる）・test_radical_group（おなじなかまの漢字テスト。部首を示し、同じ部首の字を語の□に書く。2〜4年か9・8・7級だけ。字数は14字か22字で、同じ部首の字を2字以上ずつ入れる）・test_jukugo（熟語の一字テスト。語の1字をカタカナにし、その字を漢字で書く。5・6年か6・5級だけで、5年・6級は三字の語、6年・5級は四字の語。字数は16字か24字で、語は自動で選ぶ）・test_two_readings（二つの読みテスト。同じ字の音読みの語と訓読みの語を2つの文で1組にし、線を引いた語の読みを書く。1〜4年か10〜7級・準2・2級だけで、字数は8字か12字。語は自動で選ぶ）・test_shikibetsu（漢字識別テスト。三つの熟語の□に共通する1字を10字の群から選んで書く。4・3級だけで、字数は10字か15字。語とはずれの字は自動で選ぶ）・test_tsukuri（熟語作りテスト。4年・7級は上の字の前と後ろに付く字を選び肢から選び、5年・6級は同じ読みの字を群から選んで熟語を作り、6年・5級は意味の文に合う熟語を群の字で作る。4〜6年か7〜5級だけで、字数は4年・7級が10字か15字、5年・6級が4字か6字、6年・5級が10字か15字。語・相手の字・はずれの字は自動で選ぶ）・test_kana_blank（よみがなの一字テスト。熟語の読みの1字を□にし、ひらがな1字を書く。1・2年か10・9級だけ）・test_kana_choice（正しいよみがなテスト。正しい読みと誤りの読みから正しいほうの番号を書く。1年か10級だけ）・test_char_pair（対となかまの字テスト。対やなかまの語を手がかりに□の漢字を書く。1・2年か10・9級だけで、字数は14字か22字。手がかりは自動で選び、答えが別の問題の手がかりに見える字の組み合わせは作らない）・test_kanji_choice（正しい漢字テスト。熟語の1字をひらがなにし、正しい漢字の語と形の似た字の語から正しいほうの番号を書く。2年か9級だけで、字数は8字か16字。語と誤りの字は自動で選ぶ）。省くと test_mixed。 | |
| practiceMax | No | 練習（format=practice）の1枚に載せる字数の上限。3字までなら3、6字までなら6（字の練習回数ではない）。練習のときは必須。 | |
| learningScope | No | 学習範囲。省くと小学校の教育漢字。漢検は {system:'kanken', level:10〜3、"pre2"（準2級）、2（2級）}。 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations present the bar is lower, but the description still adds real behavioral context: the 30-day link expiry, that no save/PDF is produced, that out-of-range write/read counts return proposals, that test_strokes returns only errors with no proposals, and that a title leaking answer characters is rejected. It stops short of permissions or persistence details.
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 and negatives are front-loaded, but the body is a dense run-on enumeration of 22 formats that repeats '1問の差し替えはできない' roughly a dozen times. The length is partly justified by the format surface, yet the repetition and lack of grouping hurt scannability.
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 7-parameter, 22-format tool with no output schema, the description covers return values (question list plus link), all format variants and their grade/level and character-count constraints, and the no-save/no-PDF boundary. Minor gaps remain, such as the practiceMax requirement being left to the 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 description coverage is 100%, so the baseline is 3. The description mostly restates the already-exhaustive format enum and its character-count rules rather than adding semantics beyond the schema, though it does supply the default format when omitted.
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 first sentence states a specific verb and resource (creates an A4/24-cell worksheet draft by combining existing questions) and names the return payload (question list and a 30-day confirmation link). It also carves out a clear boundary ('プリントの保存と PDF の作成はしません'), so an agent can separate it from the check/replace siblings.
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 default ('format を省くと test_mixed') and detailed per-format applicability by grade/level, and the repeated '1問の差し替えはできない' notes implicitly route single-question edits to replace_question. However, it never explicitly names the sibling to use for replacement or exclusion, leaving that routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
算数の型（型を探した結果の variantId）と問題数から A4 の紙の案を作り、確認用の短いリンク（30日有効）と、行ごとの見出し・問題数・足りない分・見本を返します。count を省いた行は1枚が埋まるまで入れます。紙が5枚を超える案は作れません。紙の保存・PDF・画面でとくはリンク先のサイトで行われます。
| Name | Required | Description | Default |
|---|---|---|---|
| lang | Yes | 紙の言語（ja・en・zh・ko・es）。 | |
| items | Yes | 紙に並べる型（1〜10行。同じ型は1行にまとめる）。 | |
| title | Yes | 紙の題（1〜60文字）。 |
学年の算数の型（出題の変種）を最大20件、問うこと・数の範囲・答えの形・作れる問題の数・見本1問（問題文と答え）とともに返します。unitId か keywords のどちらかが要ります。型の説明は日本語なので、keywords は日本語の言葉で当たります。
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | 見本と問題の数の言語（ja・en・zh・ko・es）。省くと ja。 | |
| grade | Yes | 学年（1〜6）。 | |
| unitId | No | 単元ID（MU-G1-… の形。単元の一覧が返す ID）。 | |
| keywords | No | 型の名前・説明・単元の名前に当てる日本語の言葉（例: くり上がり・2けた・時こく）。 |
指定した字の既存の問題を最大20件、問題文と答え付きで返します。プリント案の1問を差し替える候補になります。
| Name | Required | Description | Default |
|---|---|---|---|
| char | Yes | 候補を調べる字（1字）。 | |
| type | No | 熟語（書き）・読み・送りがなで絞る。 | |
| grade | No | 教育漢字のとき、プリントの学年。省けば字の配当学年。 | |
| learningScope | No | 学習範囲。省くと教育漢字。漢検の級を指定すると、その級の範囲の問題だけを返す。 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds non-annotation context: a hard cap of 20 results and the fact that returned items include both question text and answer. It omits error or permission behavior, but the added return-shape and limit info is genuinely useful.
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 with no filler; the return behavior and cap are front-loaded, followed by the usage context. Every clause 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?
No output schema exists, so the description must convey returns, and it does (max 20 items, question text and answer). For a read-only, fully schema-documented tool this is nearly complete; only edge behavior (e.g., what happens when fewer than 20 exist) is 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?
Schema description coverage is 100%, so char, type, grade and learningScope are already documented in the schema. The description only references '指定した字', adding no meaning beyond the schema baseline.
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 concrete verb and resource ('指定した字の既存の問題を...返します'), a quantity bound (最大20件), and the return content (問題文と答え付き). The second sentence positions it as the candidate-gathering step for 'プリント案の1問を差し替える', which implicitly contrasts it with replace_question, though no sibling is named 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?
'プリント案の1問を差し替える候補になります' gives a clear use context (gathering candidates before a swap). It does not spell out when NOT to use it or name an alternative tool directly, but the intent is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
学年（1〜6）の算数の単元を教科書の順に、単元ID・名前（日本語）・作れる型の数とともに返します。
| Name | Required | Description | Default |
|---|---|---|---|
| grade | Yes | 学年（1〜6）。 |
プリント案の1問を同じ字の別の問題に差し替えた新しいプリント案を作り、新しい問題一覧と確認用リンクを返します。元のリンクは元の内容のまま残ります。
| Name | Required | Description | Default |
|---|---|---|---|
| index | Yes | 差し替えるマスの位置（問題一覧の index。0始まりで、番号とは別）。手本・空白のマスは差し替えられない。 | |
| proposalId | Yes | 差し替えるプリント案の ID（proposalId）。 | |
| replacement | Yes | 差し替え先の問題の ref（差し替え候補の検索結果に含まれるもの）。対象マスと同じ字に限る。 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a non-destructive, non-idempotent mutation (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds genuinely new behavior: it creates a NEW proposal rather than editing in place ('新しいプリント案を作り'), and the original link retains its original contents. That immutability guarantee is not derivable from 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?
Two sentences, no padding, and the primary effect (new draft created) is front-loaded before the secondary guarantee (original link unchanged). Every clause 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?
No output schema exists, so the description carries the return-value burden and does so: it names the new question list and the confirmation link. Combined with the immutability note and full schema coverage, an agent has everything needed to call it 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 description coverage is 100%, and the schema itself documents index (0-based, template/blank cells not replaceable), proposalId format, and the replacement ref structure. The description adds no parameter detail beyond that, so 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?
States a specific verb and resource: replacing one question in a worksheet draft with another using the same character, and producing a new draft. It also clarifies the output (new question list + confirmation link) and that the original link is untouched, which is a strong differentiator against find_replacement_questions. It stops short of naming sibling tools 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 workflow is implied: the replacement candidate comes from the search results ('差し替え候補の検索結果に含まれるもの'), which points the agent toward find_replacement_questions. However, the description never states when to use this over alternatives or any prerequisites, leaving routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_available_kanjicreate_kanji_worksheetcreate_math_worksheetfind_math_problem_typesfind_replacement_questionslist_math_unitsreplace_questionKanji worksheets (Kanken 10-2, radicals, antonyms, yojijukugo, wrong kanji). Review link, no login.
Free printable kids activities: word searches, mazes, color by number, sudoku and more.
Search, compare and read reviews of 350+ homeschool curricula. Read-only, no account needed.
Make Anki, Quizlet, Mochi and Brainscape decks and review your vocabulary from the chat.
Add one secure layer between your agents and this server.
