Read-only HSK vocabulary, graded Chinese readings and an HSK level estimate for any Chinese text. Six tools, no API key needed.
Scored across 6 tools
Each tool has a clearly distinct purpose: check_text_level computes a level, get_level_check_link returns a URL, list_readings vs get_reading differ by list vs single item, and list_words_by_level vs lookup_word differ by listing vs targeted lookup. No two tools perform the same action, so misselection is unlikely.
All tool names follow a consistent verb_noun snake_case pattern (check_text_level, get_level_check_link, get_reading, list_readings, list_words_by_level, lookup_word). The convention is predictable and readable throughout.
Six tools is well-scoped for an HSK learning assistant covering level checking, readings, and dictionary lookup. Each tool earns its place without redundancy or missing essentials.
The surface covers level estimation (check_text_level), sharing (get_level_check_link), graded readings (list_readings, get_reading), and vocabulary (list_words_by_level, lookup_word). Together they form a complete read-only toolkit for the stated domain with no obvious gaps.
Estimate the HSK level of Chinese text (up to 5000 characters).
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It adds one genuinely useful trait — the 5000-character input limit — but says nothing about permissions, rate limits, whether the estimate is deterministic, or how partial/unknown characters are handled.
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 the action and resource front-loaded and the constraint folded in without waste. Nothing is padded or repeated.
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 must explain what an 'estimate' returns — an HSK band, a numeric score, confidence, or a per-character breakdown. It only implies a level and omits the return shape entirely, leaving a real gap for a tool whose whole value is its output.
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% for the single 'text' parameter, so the description should compensate. It contributes the 5000-character limit, which is meaningful parameter context, but gives no detail on expected script (simplified vs traditional), encoding, or whether the input is plain prose vs mixed content.
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 ('Estimate') and resource ('HSK level of Chinese text') and adds a scope constraint (up to 5000 characters), so the agent knows exactly what this tool produces. It does not name or contrast with the related sibling 'get_level_check_link', so routing between the two is left to inference 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?
There is no when-to-use or when-not-to-use guidance, and no alternative is mentioned despite a plausibly overlapping sibling ('get_level_check_link' and 'list_words_by_level'). The agent must guess the context in which this estimation is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the HSK Studio level check page link. Send learners there to check their own text and share the result.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 does convey the behavior that the check happens externally on a web page and the result is shareable, which is useful, but it says nothing about link permanence, authentication requirements, or rate limits.
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 resource being fetched and followed by the actionable guidance. No filler or repetition.
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 parameters, the description needs only to establish what is returned (a page link) and its purpose, which it does. It could be marginally more complete by indicating the return type or that the link is a URL string, but the gap is minor.
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 schema has nothing to document and there is no parameter semantics to compensate for. Baseline 4 applies.
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 ('Get the HSK Studio level check page link') and clarifies what the link is for (learners checking their own text). It is clear in isolation, though it never names the closest sibling, check_text_level, so the distinction between 'return a link' and 'perform the check' 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?
'Send learners there to check their own text and share the result' gives an implied when-to-use: this is for handing the check off to the learner rather than running it yourself. However, it never explicitly says when to prefer this over check_text_level, nor any exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one graded reading: text, HSK level and the vocabulary in it. Ids come from list_readings.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the disclosure burden. It usefully reveals the return contents (text, level, vocabulary), which matters since no output schema exists, but says nothing about error behavior for an unknown id or any access constraints.
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, zero filler, with the core purpose front-loaded and the id-provenance hint appended. Nothing extraneous.
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 single-parameter read tool with no annotations and no output schema, the description covers both the operation and the return shape. Missing only id format details and failure-mode behavior.
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% and the single 'id' parameter has no type or format details. The description compensates partially by clarifying the id is a reading id sourced from list_readings, but adds no syntax or example.
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 ('Get one') and resource ('graded reading'), then enumerates the returned contents (text, HSK level, vocabulary). This clearly separates it from the plural sibling list_readings and the word-level tools lookup_word/list_words_by_level.
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 sentence 'Ids come from list_readings' tells the agent the prerequisite step and routes it to the correct sibling for obtaining an id. It gives clear context but no explicit exclusions (e.g., when to prefer lookup_word for vocabulary detail).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the graded Chinese readings with their computed HSK level.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 conveys that this is a listing of readings with an HSK level, but says nothing about ordering, result size, pagination, or whether the list is exhaustive or filtered by any implicit user context.
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 with no filler; the verb leads and every clause carries information about the resource and its returned attribute.
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 characterize the return value more fully. It tells the agent each item has a "computed HSK level", but omits fields (title, text, id) and any notion of ordering or completeness, leaving the response shape partly unknown.
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 document; baseline 4 applies. Schema coverage is 100% and the description correctly adds no spurious parameter claims.
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 ("List") and resource ("graded Chinese readings") plus the salient returned attribute (computed HSK level). It implicitly contrasts with the singular sibling get_reading, but never names or explicitly differentiates itself from list_words_by_level or lookup_word.
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 indication of when to call this versus get_reading (single reading), list_words_by_level, or lookup_word. No prerequisites, no mention of whether any filtering or pagination is available. Usage must be inferred entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List dictionary words of one HSK level (1 to 7; 7 is the HSK 7-9 band), in syllabus order.
| Name | Required | Description | Default |
|---|---|---|---|
| level | Yes | ||
| limit | No | ||
| offset | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It does disclose one useful trait, the syllabus ordering of results, but says nothing about pagination semantics despite the presence of limit/offset, nor about permissions, result size, 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?
A single compact sentence with the core action front-loaded and the disambiguating level note in parentheses. No filler, and the essential constraint is stated first.
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 list tool with no output schema, the description should say what a returned word looks like and how limit/offset control paging. Neither is covered, and default behavior when limit/offset are omitted is undocumented.
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 all three parameters. It adds real meaning for 'level' by explaining that 7 means the HSK 7-9 band, which the schema's min/max cannot convey, but 'limit' and 'offset' are left completely 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?
The description states a specific verb and resource ('List dictionary words of one HSK level') and clarifies the level semantics, including that 7 maps to the HSK 7-9 band. It does not explicitly distinguish itself from siblings like lookup_word or list_readings, but the resource and filter are unambiguous enough for an agent to select it.
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 statement of when to use this tool versus lookup_word (single-word lookup) or check_text_level. 'In syllabus order' hints at a browsing/study use case, but no context, prerequisites, or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up a Chinese word, pinyin or English word in the HSK Studio dictionary. Returns pinyin, meaning, HSK level and a link to show the learner.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Chinese word, pinyin or English word |
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 does disclose the return payload (pinyin, meaning, HSK level, link), which is genuinely useful given there is no output schema, but it says nothing about match behavior (exact vs fuzzy), what happens when the word is not found, or any auth/rate considerations.
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 tight sentences: the first establishes the action and scope, the second establishes the return. Zero filler and the essential information 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?
For a one-parameter tool with no output schema, the description covers both input expectations and return fields, which is close to sufficient. The only meaningful omission is not-found/fuzzy-match behavior, which matters for a dictionary lookup but is not required to call the tool 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% for the single parameter, and the description merely restates the same three accepted forms (Chinese word, pinyin, English word) already documented in the schema. 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?
States a specific verb+resource ("Look up a Chinese word... in the HSK Studio dictionary") and names the accepted input forms, so the agent knows exactly what this does. It does not explicitly differentiate itself from siblings like list_words_by_level or get_reading, but the singular 'word lookup' framing makes the distinction reasonably inferable.
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 or when-not-to-use guidance and no named alternative, despite several siblings (list_words_by_level, list_readings, check_text_level) that an agent could plausibly confuse with a lookup. Usage is only weakly implied by the verb 'look up'.
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_text_levelget_level_check_linkget_readinglist_readingslist_words_by_levellookup_word
Add one secure layer between your agents and this server.