xiaoya-teacher-mcp-server

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v1.5.2
Disambiguation4/5
Most tools have distinct purposes, but some overlap exists between general create_question and specific question type creators, and between download_file/get_answer_file. The detailed descriptions help mitigate confusion.
Naming Consistency4/5
Predominantly uses verb_noun snake_case, but there are minor deviations like 'office_create_questions', 'revise_student_mark', and 'configure_paper_basics' that break the pattern.
Tool Count3/5
At 59 tools, it's on the heavy side for a single server. While the educational domain is broad, some tools could be consolidated (e.g., summary vs detail queries). Still, the count is justifiable for the scope.
Completeness4/5
Covers a wide range of teacher tasks: authentication, resource management, question creation (multiple types), paper configuration, grading workflow, attendance, and discussions. Minor gaps like creating tests/tasks or student management are present but may be out of scope.
Average 3.2/5 across 59 of 59 tools scored. Lowest: 1.7/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 5 commits in the last 12 weeks
- Last stable release on July 9, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full responsibility for behavioral disclosure. It only states the purpose without mentioning side effects, required permissions, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (4 Chinese characters) but lacks substantive content. It is under-specified rather than concise, failing to provide useful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (many parameters, nested question object, sibling tools) and absence of output schema, the description fails entirely to provide needed context about usage, return values, or the internal structure of the question object.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (75%), so the description does not need to repeat parameter info. Baseline 3 applies; the description adds no value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建简答题' is a tautology, essentially repeating the Chinese translation of the tool name. It does not provide any new information about what the tool does, making it minimally helpful for distinguishing from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives (e.g., create_question, other specific question creators). No prerequisites, exclusions, or context for when this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavioral traits. The description '创建多选题' provides no information about side effects, return values, permissions, or any other behavioral aspects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one phrase) but lacks any structure or useful content. It fails to provide value beyond the tool name, making it under-specified rather than efficiently concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema with nested objects and many options, the description is woefully incomplete. It does not explain the creation process, return values, or how to use the parameters, leaving the agent with insufficient context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 75%, meaning the schema already describes most parameters. The description adds no new meaning beyond the schema, as it only states the tool's function. The schema's parameter descriptions are detailed, so the description does not need to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建多选题' translates to 'Create multiple choice question', which states the verb and resource but lacks specificity to distinguish it from sibling tools like create_single_choice_question or create_true_false_question. The purpose is clear but minimal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. The description does not indicate when to use this tool over alternatives, nor does it mention any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description offers no behavioral information beyond the tool's name. It does not disclose that this is a mutation operation, any required permissions, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is minimal but fails to convey useful information. While concise, it does not earn its place as it adds no value beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested object, multiple parameters), the description is severely lacking. It does not explain the tool's purpose, return values, or constraints, making it completely inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is high at 75%, so the baseline is 3. The description adds no parameter information beyond what the schema provides, meeting the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建附件题' is a direct translation of the tool name, which is a tautology. It does not add any differentiation from sibling tools such as create_code_question or create_multiple_choice_question.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. No context or exclusions are mentioned, leaving the agent to infer usage solely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as side effects, permissions, or whether the action is reversible. For a creation tool, this omission is significant.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (one phrase) and lacks substantive content. While concise, it is undersized and fails to provide necessary information, making it ineffective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (3 required parameters, no output schema, creation operation), the description is incomplete. It lacks behavioral context, return value explanation, and usage hints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The tool description itself does not discuss parameters, but the schema descriptions are adequate. Thus, no additional value is added, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建空白答案项' is a direct translation of the tool name, essentially a tautology. It does not provide any additional specificity beyond the name, nor does it distinguish this tool from similar siblings like create_answer_item, create_question, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus alternatives (e.g., create_answer_item). No context about prerequisites, order of operations, or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Create answer item', implying a mutation, but fails to mention authentication, side effects, or idempotency. This is insufficient for a write operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (3 characters) and underspecified. It does not earn its place as it adds minimal value beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the number of sibling tools and no output schema, the description should explain the tool's role (e.g., creating a student's answer for a question). It lacks context about the user, result, or relationship to other tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with clear descriptions for both parameters. The description adds no additional meaning, so it meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建答案项' (Create answer item) states the action and resource but is too terse to distinguish from siblings like 'create_blank_answer_items' or 'delete_answer_item'. The purpose is moderately clear but lacks specificity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not indicate when to use this tool versus alternatives (e.g., 'create_blank_answer_items') or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description is only 3 characters, offering no behavioral insights. Important behaviors (e.g., the tool creates a question within a paper, requires program_setting with code_answer and test cases, modifies the paper's question list) are entirely absent from the description, relying solely on the input schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At 3 characters, the description is extremely short, but for a complex tool with many nested parameters and sibling distinctions, this is under-specification. Conciseness should not sacrifice necessary context; a slightly longer description that summarizes key aspects would be more valuable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the high complexity (nested objects, many fields, no output schema), the description is far from complete. It does not mention return values, prerequisites (e.g., existing paper), or the effect on the paper's question list. The schema provides detail but the description fails to provide a holistic overview.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning all parameters have detailed descriptions in the schema. The tool description itself adds no additional parameter meaning, so a baseline score of 3 is appropriate. The description does not compensate or enhance understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建编程题' clearly states the action (create) and resource (programming question), but does not distinguish it from other create_*_question tools in the sibling list. A more specific description highlighting unique aspects (e.g., 'Creates a coding question with test cases and program settings') would improve differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like create_multiple_choice_question or create_fill_blank_question. Sibling tools suggest a context of exam question creation, but no explicit usage context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. It does not mention any behavioral traits such as side effects (e.g., creating a question in a paper), required permissions, rate limits, or what happens on success/failure. The agent has no insight into the tool's behavior beyond the fact that it creates something.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (one phrase). While conciseness is valued, this is under-specification. It lacks essential details such as what the tool returns, how to use it, and important caveats. The description does not earn its place because it provides almost no useful information beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (nested TrueFalseQuestion object, 4 parameters, no output schema), the description is wholly inadequate. It should explain the purpose of 'paper_id', the structure of 'question', and what the response looks like. The current description leaves the agent with no contextual understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (75%), meaning the schema already documents most parameters well. The description adds no additional information about parameters like 'paper_id', 'need_parse', or 'need_detail'. While the description is minimal, it does not detract; however, it also does not add value 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建判断题' clearly states the action (create) and resource (true/false question). It is a specific verb+resource combination, making the tool's purpose immediately understandable. However, it does not differentiate from sibling tools like 'create_single_choice_question' or 'create_multiple_choice_question', but the tool name itself provides that distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention context, prerequisites, or conditions for use. The agent is given no information about typical scenarios, required permissions, or when to prefer this tool over other question creation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only says 'create' without disclosing side effects, permissions needed, or whether the operation is idempotent. The agent cannot assess risks or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but insufficiently informative. For a tool with 4 required parameters and an enum, more explanation is needed to be useful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 params, enum types, no output schema), the description lacks critical context such as success behavior, constraints, or examples. The agent is left unsure about how to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters, so baseline is 3. The description adds no extra meaning beyond what is in the schema (e.g., meaning of type_val values or how to obtain group_id).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create new educational resource' clearly states the action and object. It distinguishes from siblings like 'delete_course_resource' and 'update_resource_name', but could be more specific about the resource types supported.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., 'batch_create_questions' or 'create_question'). No prerequisites or conditions are mentioned, leaving the agent unaware of when this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states 'create fill-in-the-blank question' and omits any information about side effects, permissions, rate limits, or return value. The agent cannot infer non-obvious behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (4 characters in Chinese). While it is front-loaded, it sacrifices necessary detail for brevity. It is not optimally helpful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested FillBlankQuestion object, multiple optional parameters) and no output schema, the description is severely lacking. It does not mention required fields like paper_id and question, nor does it explain the structure of the question object.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (75%), meaning the schema already documents most parameter meanings. The tool description adds no extra parameter information, so it meets the baseline but does not improve understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建填空题' clearly indicates the action (create) and the resource (fill-in-the-blank question). It is specific enough to know what the tool does, but it does not differentiate from other question creation tools like create_single_choice_question. The name already conveys this, so the description adds minimal value.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_multiple_choice_question, create_code_question). The description lacks context for choosing this specific question type.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavior. It only states 'delete' without mentioning irreversibility, permissions needed, or effects on related data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (a single phrase) but lacks important details, making it minimally functional. Conciseness is achieved but at the cost of completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive operation with two parameters and no output schema, the description should note confirmation of deletion or irreversible effects. It fails to provide this context, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers 100% of parameters with clear descriptions. The tool description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'delete' and the resource 'educational resource'. It is specific enough to distinguish from siblings, as there is no other delete tool with a similar name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives like batch deletion or other resource operations. Prerequisites such as obtaining group_id and node_id are provided in the schema but not in the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description is minimal. It does not disclose behavioral traits such as read-only nature, authentication requirements, or any side effects. The name implies a query but is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence), but it is too brief to convey sufficient information. While conciseness is positive, it sacrifices completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter and no output schema, the description should at least hint at the return value or behavior. It does not, leaving the agent with insufficient context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a description for the parameter, but the tool description itself does not add meaning beyond the schema. The schema already explains how to obtain group_id, so the description provides no additional value for parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '查询课程目录排序设置' (Query course catalog sort settings) clearly states the action (query) and the resource (course catalog sort settings). It distinguishes from sibling tools which are mostly create/update/delete operations, so the purpose is clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Sibling tools include many query tools (e.g., query_teacher_groups, query_group_classes), but the description does not differentiate or specify contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states 'query', implying a read operation, but lacks details such as what the snapshot contains, whether it's idempotent, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (a single phrase), but it sacrifices informativeness for brevity. While it is not verbose, it lacks structure and could benefit from additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema, the description should explain the return value (e.g., what fields the snapshot contains). It fails to do so, leaving the agent without a clear understanding of what data to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% as the only parameter (group_id) has a description. The tool description does not add any additional semantic information beyond what is already in the input schema, so it meets the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'query' and resource 'course group overview snapshot', indicating a retrieval operation. However, it does not distinguish this tool from sibling tools like query_group_classes or query_group_tasks, which also query group-related information.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines are provided. The description does not specify when to use this tool over alternatives, nor does it provide any context on prerequisites beyond the parameter hint that group_id comes from query_teacher_groups.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry behavioral disclosure. It does not mention whether the update is partial or full, idempotent, or what side effects occur. The schema implies optional fields for partial updates, but this is not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but does not provide substantial value. It is not front-loaded with critical information; it merely restates the function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 13 parameters and no output schema, the description is insufficient. It does not explain update semantics, error handling, or typical use cases. The schema covers parameters well, but the description adds no context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema. It does not explain parameter relationships or usage patterns.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool updates general configuration of any question, but does not differentiate from siblings like update_question_options or update_code_test_cases. It is specific about the resource but lacks sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, limitations, or context where other tools are preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It only states a return value without disclosing potential side effects (e.g., whether using the 'refresh' parameter incurs a cost). No information about 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence. While it lacks structure, it is appropriately front-loaded and contains no redundant information for such a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 optional parameter, output schema present), the description is minimally adequate. However, it omits behavioral details and parameter explanation, leaving room for improvement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not mention the 'refresh' parameter at all. The input schema has 0% description coverage, so the description adds no semantic meaning beyond what the schema provides (which itself lacks descriptions). The agent would not know how the parameter affects behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '返回当前认证信息' (return current authentication information), which specifies the action (return) and resource (authentication info). There are no sibling tools related to authentication, so it is well-distinguished.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool or when an alternative would be better. There are no prerequisites, context examples, or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as whether the operation is destructive, idempotent, or requires specific permissions. For a batch update tool, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence in Chinese with no unnecessary words. However, it lacks structural elements like bullet points or separate sections, which could improve readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a batch mutation tool with no output schema or annotations, the description should cover aspects like success/error handling, idempotency, or scope of update. It is incomplete as it only states the basic functionality.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter having a clear description (group_id source, node_ids as list, download as enum with values 1=forbid, 2=allow). The description adds no additional semantic value beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (batch update) and the target (resource download attributes). It distinguishes from siblings like batch_update_resource_visibility or update_resource_name. However, it could explicitly mention 'download permission (allow/forbid)' to avoid ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives, no mention of prerequisites or context. The description simply states what it does without any usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose important behavioral traits such as whether deletion is irreversible, required permissions, or cascading effects on related data. For a delete operation, transparency is critically lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise at one short sentence, but it is appropriately sized for the simple action. Could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with 3 required parameters and no output schema or annotations, the description is insufficient. It lacks details on permanence, permissions, and consequences, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with clear parameter descriptions. The tool description does not add any additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('delete') and the resource ('answer item/option of a question'). It distinguishes itself from sibling tools like 'create_answer_item' and 'move_answer_item'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives, no prerequisites or context for use. The description only states what it does without any usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. It mentions optional submission but fails to disclose that the operation modifies existing data, requires permissions, or error cases (e.g., need allow_reopen for submitted papers). Behavioral traits are insufficiently disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, extremely concise, but at the expense of essential details. For a tool with 4 parameters and nested objects, it should include more context. It is under-specified rather than efficiently concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 params, nested objects, no output schema), the description is incomplete. It lacks explanation of grading_context, relationship to get_student_grading_bundle, and behavioral notes on submission state and error handling. The parameter descriptions partially compensate but the overview is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no extra meaning beyond what the schema provides; it does not explain how to obtain or use grading_context despite it being critical. No additional value provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (batch write scores/comments for multiple questions of a single student) and specifies the optional submission of the whole paper. It uses specific verb (write) and resource (scores/comments), and distinguishes from sibling tool grade_student_question which handles single questions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool vs alternatives (e.g., for batch grading vs single question grading). It also does not mention prerequisites like obtaining grading_context from get_student_grading_bundle, which is required by the schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only says 'adjust order' without mentioning side effects, permissions, reversibility, or what happens if the order array is invalid. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one short sentence) and front-loaded. It wastes no words, though it could arguably benefit from slightly more detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 params, no output schema, no nested objects), the description is minimally adequate. It states the core operation but omits context about the ordering array and potential constraints, making it sufficient but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with clear descriptions for both parameters. The description adds no extra meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it adjusts the order of answer options for any question type, which is a specific action on a clear resource. However, it does not explicitly differentiate from sibling tools like update_question_options or create_answer_item, so it loses the full point for discrimination.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor any context about prerequisites or conditions. The description only states what it does, leaving the agent to infer usage without any direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as read-only nature, permissions required, or rate limits. The tool is likely a safe query but this is not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. However, it could benefit from slightly more structure or detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so the description should clarify what the return value contains. It does not mention the structure of 'statistics details', leaving the agent with incomplete context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already explains both parameters. The tool description adds no additional parameter meaning beyond the schema, earning baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries discussion task statistics details, with a specific verb and resource. It distinguishes from siblings like 'query_group_tasks' which likely query tasks themselves, not statistics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives, no context about prerequisites or when not to use. The description only states what it does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as read-only status, permissions, or side effects. It relies solely on the minimal description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no redundancy, but it could benefit from more structure or being front-loaded with English translation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks details about output, pagination, or any procedural context. Given the presence of many sibling tools, more completeness would help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with meaningful explanations for both parameters (source of group_id and role meaning). The description does not add additional value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (query) and resource (group task notices), distinguishing it from sibling tools like query_group_tasks. However, it is brief and lacks explicit scope details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives. The description does not mention any context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description lacks behavioral details such as read-only nature, return format, or side effects. It only states a basic operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the key purpose. However, it is very brief and could include more context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool, the description is minimally adequate. It lacks details about the output, but parameters are well-referenced. Could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with parameter details linking to other tools. The tool description itself adds no further parameter meaning, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取试卷摘要' clearly states the verb (get) and resource (paper summary). It is specific but does not differentiate from siblings like query_paper.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase '推荐 AI 默认使用' implies it is recommended for default use but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose traits. It only states '获取属性' without mentioning read-only behavior, side effects, or required permissions. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no extraneous information. Every word carries functional meaning. Efficient and direct.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no description of return format. The detail_level parameter hints at output granularity (summary/full/raw), but the description does not explain what '属性' actually includes. Incomplete for a 3-parameter query tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover all parameters (100%). The description adds no new meaning beyond repeating the schema; detail_level's semantics are already explained in schema. Baseline score due to full schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (获取) and resource (资源属性) with required inputs (group_id, resource_id). It is specific enough to distinguish from sibling tools like query_course_resources, though it does not explicitly contrast them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives (e.g., query_resource_folder_snapshot). The description implies usage when group_id and resource_id are known, but lacks explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description provides no behavioral details (e.g., side effects, required permissions, mutability) and annotations are absent, leaving the agent without critical information about executing this mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence that efficiently conveys the tool's purpose and scope, though it lacks structural elements like bullet points or sections.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a mutation with no output schema and no annotations, the description is too minimal; it omits needed behavioral and contextual details for safe usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All three parameters have descriptions in the input schema (100% coverage), so the description adds no extra meaning beyond the schema, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for updating fill-in-blank answers, with a scope indicator '[仅限填空题]' that distinguishes it from sibling tools like update_short_answer_answer or update_true_false_answer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives; the description only states its scope without providing explicit usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It simply states the function without revealing side effects, prerequisites, or safety implications. For instance, it doesn't mention that the resource must exist, or whether the update is reversible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately conveys the purpose. It is front-loaded and free of unnecessary words. However, it is in Chinese, which may limit accessibility for English-only contexts.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple rename operation with three well-documented parameters, the description is minimally adequate. It explains what the tool does but lacks detail about return values (no output schema), error conditions, or how the tool interacts with related resources. No output schema is present, so some information about what happens after update would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides clear descriptions for all three parameters (group_id, node_id, new_name), achieving 100% schema coverage. The tool description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('更新', update) and the resource ('教育资源名称', educational resource name). It's specific and directly conveys the tool's operation. However, it does not differentiate from sibling tools like update_resource_sort, which also update a resource property.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For example, it doesn't mention that this tool only changes the name, not other attributes, or that it requires the resource to exist. Sibling tools like 'delete_course_resource' or 'update_resource_sort' are not mentioned in context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It does not mention any side effects, permission requirements, or whether the operation is destructive. The single sentence lacks behavioral context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with a single sentence. It is front-loaded and efficient, but the extreme brevity limits the information conveyed. Still, no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not cover what the tool returns (no output schema) or potential partial failures in batch operations. It also lacks context about the batch nature, such as constraints or limits. For a tool with 3 required parameters and no output schema, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All parameters are described in the schema with clear names and descriptions. The tool description adds no additional meaning beyond the schema, so a score of 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action (batch update) and the resource (visibility of resources within a course group). It distinguishes itself from sibling tools like batch_update_resource_download by focusing on visibility.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, such as needing a group_id or that resources must exist, nor when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description says 'one-click configure' but does not explain behavioral traits such as whether it overwrites existing settings, if it is idempotent, or what happens to unspecified parameters. The input schema indicates optional parameters default to null, which hints at non-destructive behavior, but the description adds no clarity beyond that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, making it concise and to the point. However, it sacrifices completeness for brevity; it could be slightly expanded to include key behavioral or usage notes without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not specify return values, side effects, or the scope of 'basic settings'. The tool handles 6 parameters, yet the description provides no context on how they are applied together.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All six parameters are fully described in the input schema (100% coverage), so the description adds minimal additional meaning. The description's mention of '整卷常用基础设置' implies these are common basic settings, but it does not elaborate on how parameters relate to each other or the 'one-click' concept.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly indicates the tool configures basic settings for an entire exam paper ('整卷常用基础设置'). It uses a specific verb 'configure' and resource 'paper basics', but does not differentiate from similar sibling tools like update_paper_randomization or update_paper_question_order.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternative tools. There is no mention of prerequisites, limitations, or exclusions. The user is left to infer usage from the tool name and sibling tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states it creates a blank question, omitting critical traits like authentication requirements, potential side effects, or the fact that it is a mutational operation. No information about the returned result or error handling is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. However, it is so brief that it sacrifices completeness, which prevents a perfect score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, many siblings, no output schema, no annotations), the description is incomplete. It fails to explain the creation process, returned data, or how it fits with other tools, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameter roles are well-defined in the schema. The description adds no additional semantic value beyond what the schema already provides, warranting the baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: creating a new blank question in an exam paper. It distinguishes itself from sibling tools that create specific question types (e.g., create_single_choice_question) by emphasizing 'blank' question.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the many alternative creation tools (e.g., for specific question types). The description does not mention prerequisites, limitations, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It only states the tool 'gets a summary', implying a read operation, but does not explicitly state it is non-destructive, has no side effects, or requires any permissions. The behavioral transparency is minimal and adds little beyond what the name suggests.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a parenthetical, concise and front-loaded with the core purpose. Every word is essential, no fluff or redundant information. It appropriately prioritizes the key action and context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only two parameters and is a simple query, the description is somewhat adequate. However, there is no output schema, so the agent does not know what fields the summary contains. For a complete understanding of the tool's output, additional information would be beneficial, but the current description meets a minimum viable level.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides clear descriptions for both parameters (e.g., group_id explained as obtained from query_teacher_groups, view_mode with options). The tool description does not add any additional meaning beyond the schema, so it meets the baseline of 3 for high schema coverage (100%). No extra semantic value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取课程资源摘要' clearly states the tool retrieves a summary of course resources. The parenthetical '推荐 AI 默认使用' suggests it is the preferred default, but does not explicitly differentiate from sibling tools like 'query_course_resources' which likely returns detailed data. However, the name and brief description imply a concise overview, making the purpose reasonably clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The parenthetical '推荐 AI 默认使用' implies it is the default, but there is no mention of when not to use it or what other tools (e.g., 'query_course_resources') cover different needs. The agent is left to infer usage context from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the tool queries a list, with no disclosure of side effects, read-only guarantee, authentication needs, or rate limits. For a simple query tool, minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose. No unnecessary words, and front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (1 param, no output schema, no annotations), the description is adequate but missing details about the return format (e.g., list of class names or IDs). An agent might not know what to expect from the output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter, which already explains its source (query_teacher_groups). The tool description adds no additional parameter-level meaning, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries the class list for a course group, with a specific verb and resource. It distinguishes implicitly from sibling tools like query_teacher_groups, but does not explicitly differentiate itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. The parameter description hints at a prerequisite (obtaining group_id from query_teacher_groups), but no when-not or alternative context is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the basic function. It does not disclose behavioral traits such as permissions, data limits, read-only status, or pagination behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence. While it lacks front-loaded structure, it is efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is too minimal. It does not explain what a snapshot contains or how to interpret results, making it incomplete for context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
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 adds no additional parameter meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries direct child resource snapshots under a specified folder. The verb 'query' and resource 'resource folder snapshot' are explicit, and the constraint 'direct child' distinguishes it from sibling tools like query_course_resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives. No explicit when-not or alternative tool suggestions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear the full burden. It only states that the tool updates settings but fails to disclose important behavioral traits such as whether changes are permanent, what happens to existing randomization, or any prerequisites (e.g., paper must exist). As a mutation tool, this lack of transparency is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no unnecessary words. It efficiently conveys the core purpose. However, it could be slightly improved by adding context that is currently missing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (4 parameters, mutation, no output schema), the description is too terse. It omits critical context such as return values, side effects, and prerequisites. The schema provides parameter details, but the description should complete the picture.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%; all four parameters are described in the schema. The description adds no additional meaning beyond the schema. Under the rule that high coverage yields a baseline of 3, this score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb '更新' (update) and the resource '试卷的题目和选项随机化设置' (paper question and option randomization settings), which includes both shuffling and scoring type. This distinguishes it from sibling tools like update_paper_question_order (order only) and update_question_options (options content).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Sibling tools like update_paper_question_order or update_question exist, but no when-to-use or when-not-to-use information is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. The description only states that the tool updates sorting, without revealing any side effects, permissions required, or whether the operation is destructive. For a mutation tool, this is insufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the tool's purpose. It is front-loaded and efficient, though it could be slightly more structured with additional context. Still, it earns its place with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema, no nested objects), the description is too minimal. It lacks behavioral transparency and usage guidance, making it less useful for an AI agent to decide when to invoke it or understand its full impact.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers both parameters with descriptions, achieving 100% coverage. The tool description does not add parameter details, but baseline is 3 since the schema does the work. The description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action: updating the sorting of resources within a course group. It uses a specific verb ('update') and resource ('sorting of resources within a course group'), distinguishing it from sibling tools like 'move_resource' which deals with moving individual resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'move_resource' or other batch update tools. It does not mention prerequisites or context of use, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It only states 'update' without detailing side effects, permissions, or idempotency. For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one short sentence). It is front-loaded and immediately clear, though it may be too brief for full comprehension.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters, no annotations, and no output schema, the description is inadequate. It lacks context on return values, side effects, and usage scenarios, making it incomplete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already explains parameters. The description adds no additional meaning beyond the title, resulting in baseline performance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the tool updates reference answers for short answer questions. It clearly identifies the resource and action, distinguishing it from sibling tools like update_fill_blank_answer. However, it does not elaborate on 'reference answer' scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use only for short answer questions, but provides no explicit guidance on when to use this versus alternatives. No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only repeats the tool name without disclosing any behavioral traits such as side effects, required paper association, or return behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence. It is front-loaded and avoids verbosity, though it may be too minimal for a tool with a complex nested schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The schema provides rich detail for parameters and nested objects, but the description lacks context about the paper_id linkage, usage within a paper, or how it differs from create_question. Adequate given schema, but could improve.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 75% with detailed parameter descriptions (e.g., title_md, options). The description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '创建单选题' clearly states the verb 'create' and the resource 'single choice question', distinguishing it from siblings like create_multiple_choice_question, create_true_false_question, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. With many question creation siblings, explicit context on prerequisites, paper_id requirement, or when to choose this over others is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as read-only nature, side effects, rate limits, or output format. The query verb implies safe operation, but it is not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise Chinese sentence, efficient for a simple tool. However, it lacks structure and could benefit from additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 2 parameters no output schema, the description is minimally adequate but does not cover potential errors, pagination, or result details. It serves the basic purpose but leaves gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with clear parameter descriptions (group_id source, detail_level options). The tool description adds no extra meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries all tests/exams/tasks published by a course group, using specific verb and resource. Among siblings like query_group_classes or query_group_discussion_task_detail, it distinctly identifies its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives. No prerequisites, exclusions, or contextual hints beyond the basic purpose. The parameter description in schema references obtaining group_id from another tool, but the tool description itself is silent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits like read-only nature, idempotency, permissions, or effects. The tool likely performs a read operation, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose. It is front-loaded and efficient, though could benefit from additional structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about output format, pagination, ordering, or error handling. While the tool is simple, more context would be helpful for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. The tool description adds no extra meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '查询单次签到的学生列表' clearly states the action (query), resource (attendance students), and scope (single attendance), distinguishing it from sibling tools like query_attendance_records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 alternatives such as query_attendance_records. No prerequisites, exclusions, or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only states the function. It does not disclose behavioral traits like read-only, authentication needs, or scope of results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary text, directly conveys the purpose. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a no-parameter tool with no output schema, the description is minimal but adequate. However, additional context about the nature of the query (e.g., returns list or summary, scope like current user) would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so the description does not need to add parameter details. The schema coverage is 100% (empty schema), and the description is sufficient for a zero-parameter tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'query teacher's course groups', a specific verb+resource combination. However, it does not differentiate from sibling tools like query_group_classes or query_group_snapshot.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., query_group_classes). The description lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. However, it only states the action without any details on side effects, permissions, error handling, or behavior when invalid IDs are provided. The minimal description adds little beyond the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, concise and to the point. It could include slight additional context, but it effectively communicates the core action without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with two parameters and no output schema. The description combined with the schema provides basic understanding, but the lack of behavioral details (e.g., what happens if a question ID is invalid) leaves some gaps. Completeness is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters (paper_id from query_group_tasks, question_ids as ordered list). The description adds no additional semantic value beyond what the schema already conveys, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '更新试卷的题目顺序' clearly specifies the verb 'update' and the resource 'order of questions in a paper'. It distinguishes itself from sibling tools like update_paper_randomization and update_question by focusing specifically on question order.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or typical use cases. The description is purely functional without contextual direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only mentions 'strong stability' but does not disclose behavioral traits such as whether existing questions are overwritten, validation behavior, error handling, or any destructive actions. For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the main action and supported types. It is efficient but could benefit from a second sentence to provide usage context or return values.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is complex with 4 parameters including nested objects, and no output schema exists. The description does not explain what happens on success/failure, or what the return values look like. It also omits prerequisites (e.g., obtaining paper_id from query_group_tasks), making it incomplete for a mutation operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the schema itself contains detailed descriptions for each parameter and nested types. The tool description adds minimal additional meaning beyond listing supported types, which is already covered in the schema discriminator. Thus, it meets the baseline but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: batch import of questions (official interface). It explicitly lists supported question types (單选、多选、填空、判断、简答、附件题), which distinguishes it from sibling tools that create individual questions one by one.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool is the official stable batch import interface, and lists supported types, but does not explicitly state when to use it over alternatives (e.g., creating questions individually). No when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only mentions it is unofficial and unstable. It does not disclose behavioral traits such as side effects, required permissions, or what happens on failure. For a batch creation tool with no annotation safety net, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the purpose, instability warning, and supported types. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 question types, many nested schemas) and no output schema, the description lacks high-level context about batch behavior, ordering, error handling, and what the response contains. The rich schema compensates partially, but the description is too minimal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
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 parameters thoroughly. The description adds no additional meaning to parameters beyond the list of question types, which is already implied by the tool's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for batch creating questions, lists the supported question types (单选、多选、填空、判断、附件、简答题、编程题), and distinguishes itself from sibling individual create tools by noting it is unofficial, unstable but more powerful.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description hints at when to use this over individual tools ('非官方接口,不稳定但功能更强大') but does not provide explicit guidance on when not to use it or alternatives. The context with sibling tools helps, but the description itself lacks direct usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the action without disclosing behavioral traits like permissions required, reversibility, or impact on shared access. For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. Front-loads the purpose effectively. Very concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Description is too minimal for an AI agent. It lacks details about prerequisites (e.g., resource must exist in from_parent_id) and does not mention the operation's effects. Given no annotations or output schema, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool moves a resource to a new parent folder. The verb 'move' and resource are specific, and it distinguishes from sibling tools like create_course_resource or update_resource_name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or alternatives given. The description implies its usage context (moving resources) but lacks guidance on prerequisites or when not to use it, such as when needing to reorder within the same folder.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No behavioral traits are disclosed beyond the basic action. The description does not mention side effects, destructive nature, or prerequisites. With no annotations provided, the agent lacks important behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core purpose. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a deletion tool with no annotations and no output schema, the description is minimal. It lacks information about success/failure behavior, error handling, or prerequisites. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents both parameters. The description adds no extra meaning beyond what's in the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs batch deletion of questions from a test paper. It distinguishes from sibling tools like delete_answer_item and delete_course_resource which target different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. It only states its purpose, leaving the agent to infer usage context from the tool name and siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only states 'update the option content' without detailing side effects, idempotency, permissions, or limits. This is insufficient for a mutation tool with 8 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a front-loaded constraint, making it efficient. However, it is very terse and could benefit from more structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 8 parameters and no output schema, but the description provides no context on return values, update behavior (partial vs full), or how parameters interact. The schema helps, but the description is insufficient for complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no additional parameter meaning beyond the schema; it only restates the overall purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for updating options of single/multiple choice questions. It specifies the resource ('选项内容') and action ('更新'), and the limitation to only those question types distinguishes it from generic update tools like update_question.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly restricts usage to single/multiple choice questions with '[仅限单选/多选题]', providing clear when-to-use guidance. However, it does not mention alternatives or when-not-to-use beyond the restriction, lacking explicit comparison with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear the transparency burden. It only indicates a read operation ('query') but offers no detail about side effects, authentication needs, rate limits, or other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose. No extraneous words or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple query tool with one parameter, the description provides enough context: what it does and where to find the parameter. However, given no output schema, it omits what the response contains, which may be needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter description adds value by stating that the group_id is obtained via 'query_teacher_groups', which goes beyond the schema's basic type info. With 100% schema coverage, this additional context elevates the score above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询课程组的全部签到记录情况' (Query all attendance records of a course group), specifying the verb 'query', the resource 'attendance records', and the scope 'all'. This distinguishes it from the sibling 'query_single_attendance_students' which queries individual attendance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention sibling tools like 'query_single_attendance_students' or explain scenarios for using this one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full burden. It discloses default return format but does not reveal read-only nature, authentication needs, or effects of parameters beyond schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose and key behavior, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains return format (summary vs full) and hints at parameters. Completeness is adequate for a simple query tool, though siblings could be referenced.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing baseline 3. The description adds no extra meaning beyond the schema, only mentioning detail_level which is already documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries a paper, specifying default behavior (summary) and how to get full content. It distinguishes from sibling tool 'query_paper_summary' which is likely more limited.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage via default and full content options but does not explicitly state when to use this tool over alternatives like 'query_paper_summary' or preconditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. It states it queries data and returns specific fields, implying a read operation. It does not detail auth, rate limits, or error states, but is adequate for understanding basic behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded with a step indicator and captures the core purpose efficiently. It avoids unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 parameters and no output schema, the description mentions key return values (mark_mode_id, record_id) which is helpful. However, it lacks details on pagination, error handling, or performance, leaving some gaps given the query-all nature.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds workflow context but does not significantly enhance parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries test results for all students and returns key IDs for grading. It uses specific verbs and resources, and while it does not explicitly differentiate from siblings, the context of grading step 1 distinguishes it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description marks it as the first step in grading and notes that mark_mode_id is required for subsequent steps, providing clear context for when to use it within a grading workflow. It does not specify when not to use, but the guidance is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
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 adds the key behavioral detail that the operation overwrites original test cases, but does not disclose other traits like auth requirements, rollback possibility, or effect on other data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single Chinese sentence that efficiently conveys the tool's purpose and a key behavioral trait (overwriting). It is front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 required parameters, no output schema, and no annotations, the description is too brief. It fails to explain return values, error conditions, or success/failure indicators. The overwrite warning is useful but incomplete for a complex mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter having a clear description in Chinese. The tool description adds no additional parameter information beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it updates programming question answer code and test cases, with the specific behavior of overwriting original test cases. This verb+resource structure distinguishes it from sibling tools like create_code_question (creation) or delete_answer_item (deletion).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for modifying existing test cases, but lacks when-not scenarios or prerequisites. It is clear enough for a typical update operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the action (updating answer) without detailing side effects, permissions, or whether the change is destructive. This is a major gap for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that front-loads the purpose. Every part is meaningful with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description lacks details on return values, error conditions, or prerequisites. For a simple update tool, it is minimally adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context that answer_item_id corresponds to the option to set as correct, reinforcing the schema descriptions. However, it does not add substantial new meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool updates the answer of a true/false question by setting the specified option as correct. It uses a specific verb ('update') and resource ('answer of true/false question'), and distinguishes from sibling tools like update_fill_blank_answer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly limits usage to true/false questions with '[仅限判断题]', providing clear context. However, it does not mention when not to use or suggest alternatives like update_short_answer_answer, so it falls short of full guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description clearly explains the behavior for save_path with three explicit cases: absolute path (auto-creates parent directories), existing directory (saves with original filename), and omitted (saves to system temp directory with original suffix). This is valuable behavioral information beyond the schema. However, it does not mention error handling, permissions, or what happens if the download fails.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: a single introductory sentence followed by three bullet points, each covering a specific case. Every sentence is informative and earns its place. The structure is front-loaded with the purpose and then clarifies parameter behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description does not explain the return value or success/failure indicators. It states the file is saved to disk but does not specify if there is a confirmation message or error feedback. This omission reduces completeness for an agent that needs to know what to expect after invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all three parameters described. The description adds significant nuance for save_path by explaining three distinct behaviors. For paper_id and filename, it repeats the schema. Overall, the description adds meaning beyond the schema for the key parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '获取下载链接并自动下载文件内容,保存到本地磁盘' which means 'get download link and automatically download file content, save to local disk'. It uses a specific verb (download) and resource (file), and is distinct from sibling tools that query resources or read file content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as needing a paper_id and filename from query_course_resources, but this is implicit. No explicit when-not-to-use or exclusion criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only describes the query action but does not mention side effects, permissions, rate limits, or the nature of the return data beyond the detail level.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of one sentence with two clauses that immediately convey the core purpose and usage. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and only two parameters, the description adequately explains the functionality and parameter options. However, it does not describe the structure of the returned data, leaving ambiguity about what fields are in summary vs full.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds context by explaining the default summary behavior and the effect of setting detail_level to full/raw, which goes beyond the schema's pattern description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('query') and resource ('course resources'), and distinguishes from sibling tools like query_course_resources_summary by noting that this tool returns summary by default with options for full/raw detail.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides guidance on using detail_level for different granularities (summary, full, raw). It implies when to use this tool over query_course_resources_summary, but does not explicitly state when not to use it or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the side effect of downloading attachments locally and specifies the returned fields. However, it does not confirm whether the tool is read-only or if any state changes occur beyond file download.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with main action, then specifics. No redundant or extraneous content. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description compensates by listing the returned fields and mentioning attachment behavior. It lacks detail on the structure of grading_context but is otherwise sufficient for a retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions linking to other query tools. The description does not add extra meaning beyond listing return fields, which is output-related. Baseline 3 is appropriate since schema already thoroughly documents each parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: retrieving a single student's AI grading bundle and downloading attachments. It specifies the returned fields (grading_context, manually graded items, scores/comments, student answers, attachment file_path). This distinguishes it from siblings like grade_student_paper which perform grading actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining grading bundle data but does not explicitly state when to use this tool vs alternatives (e.g., grade_student_paper for actual grading). No guidance on prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must convey behavioral traits. It states the tool queries data, implying a read-only operation. It does not disclose side effects, authorization needs, or rate limits, but for a read query this is minimally acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently conveys purpose, step context, and key return fields. No extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains what is returned (mark_paper_record_id and answer_id). It could elaborate on how parse_mode and detail_level affect output, but the schema covers their definitions. Overall sufficient for an agent in a marking workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 7 parameters have descriptions in the schema (100% coverage). The description adds only minor insight: that answer_id is required for scoring. This provides marginal added value beyond the schema, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is '[Marking Step 2]' and queries a student's complete answer content, returning mark_paper_record_id and answer_id for each question. This explicitly distinguishes it from sibling tools like 'grade_student_paper' which perform the actual grading.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It indicates that this tool is step 2 in a marking workflow and that its output is required for scoring. This provides clear usage context. However, it does not explicitly mention when not to use it or list alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description discloses key behavioral trait: default only modifies unsubmitted grading; submitted grading requires allow_reopen. Also mentions optional resubmit. Lacks broader context like permissions or rate limits, but covers the main behavioral quirk well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first states purpose, second provides essential behavioral condition. No superfluous words, highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 12 parameters, the description gives the core behavior but omits details like interplay of is_teacher_recheck or conditions for submit_after. Adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already fully documented. The description adds marginal value by contextualizing allow_reopen and submit_after but does not provide additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states '修改学生某题分数/评语' (modify student's score/comment for a question) and distinguishes from siblings like grade_student_question and submit_student_mark by focusing on revising an existing mark with optional reopen.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance: default for unsubmitted grading, explicit allow_reopen=true for submitted grading. Implicitly suggests when to use but does not explicitly list alternatives or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It discloses key behaviors: success writes scores to the student side (persistence), dependency on prior grading of all manual questions, and the need to withdraw before modifications. However, it does not mention error conditions or idempotency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with only two sentences plus a preamble. It is front-loaded with the purpose in brackets, and every sentence adds value with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description covers prerequisites, effects, and related tools. It could mention potential error states or return values, but it is largely complete for a submission action.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with descriptions explaining source values (from other tools). The tool description does not add further parameter semantics beyond what the schema provides, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '提交整卷批阅结果' (submit entire paper marking results). It distinguishes itself from sibling tools like 'grade_student_question' (grades individual questions) and 'withdraw_student_mark' (reopens grading for modifications). The title and name also reinforce this purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: it must be called after all manually graded questions have been processed via 'grade_student_question', and if modifications are needed, 'withdraw_student_mark' must be called first. This covers when and how to use the tool, though it does not list alternative tools for other scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
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 discloses that the tool reopens marking to allow modifications, but does not detail side effects (e.g., previous scores discarded, permissions required). It is not misleading but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences for the core purpose plus a brief workflow note. Every sentence contributes meaning, no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 5 parameters, the description covers the main purpose and recommended workflow. It could mention error cases or what happens to previous scores, but it is sufficient for a mutation tool with a clear task.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptive parameter names and descriptions. The tool description adds no further semantic value beyond what the schema provides, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's verb 'reopen' and resource 'submitted full-paper marking', distinguishing it from sibling tools like submit_student_mark and grade_student_question. It explicitly explains that it allows scores and comments to be modified again.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance: must confirm the teacher intends to modify submitted marks, and outlines the typical workflow of calling grade_student_question or revise_student_mark then submit_student_mark next. This clarifies when to use and what to do after.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It correctly implies a read operation by stating 'returns', but does not explicitly mention idempotence or lack of side effects. Slightly above average.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence efficiently conveys the tool's purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with an output schema, the description is complete. It tells what the tool returns without needing to detail the output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so baseline score of 4 applies. Description adds no param info, but none needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool returns server operating mode, URL, and port. It is a specific verb+resource pair that distinguishes it from siblings like auth_status or query_course_resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. While the purpose is clear, it does not mention prerequisites or scenarios. Implied usage is diagnostics but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description implies read-only behavior and discloses supported formats. Could be improved by stating behavior on unsupported files or return format, but adequate for a non-destructive tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise with two short paragraphs and bullet points. Every sentence adds unique information, no redundancy, front-loaded with key action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema or annotations, the description covers inputs, modes, and supported formats well. Lacks description of return value (Markdown string) but is otherwise complete for a read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds value by grouping parameters into modes, clarifying priority (file_path over paper_id+filename), and indicating requiredness. This exceeds the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool reads file content into Markdown using markitdown, specifies two modes (local file or course resource), and lists supported formats. This is a specific verb+resource and distinguishes from sibling tools like download_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance on when to use each mode, noting file_path is preferred and paper_id+filename are both required for course resources. Does not explicitly state when not to use, but the context is sufficient for agent decision.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It explains dual behavior (return base64 or file path), and recommends use cases. Does not cover authorization or rate limits, but is generally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise, with clear bullet points. Every sentence adds necessary information. Front-loaded with main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given only 2 parameters, no output schema, and no annotations, the description is complete. It explains inputs, two modes, and use cases sufficiently for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% already describing both parameters. Description adds value by clarifying quote_id's source and save_path's optional nature and recommended usage for image/PDF, going beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it retrieves student answer attachments (images, PDFs, files). It specifies two modes based on the save_path parameter, effectively distinguishing this from other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear when-to-use guidance for both modes (base64 for small attachments, file path for image/PDF marking with Read tool). Lacks explicit when-not-to-use or alternative tool references, but context is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description conveys key traits: can be called multiple times before submission, score upper bound from another tool, and integration with a four-step process. Lacks error behavior or permission info but sufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, front-loaded with core action, then usage conditions, then workflow. Every sentence adds value with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers when, why, and prerequisites well within the workflow context. Lacks return value description, but the output is likely minimal (success/failure). Adequate for a step in a multi-tool process.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds substantial context by indicating where each parameter value originates (e.g., query_preview_student_paper, query_test_result), enhancing understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Grade a student's question' and specifies it applies only to short answer (type=6) and attachment (type=7) questions, distinguishing it from auto-graded types and sibling tools like grade_student_paper.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to call (only for specific question types) and when not to (auto-graded types), provides score limits, mentions repeatability before submission, and outlines the prerequisite workflow including calling withdraw_student_mark if needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![xiaoya-teacher-mcp-server MCP server](https://glama.ai/mcp/servers/Sav1ouR520/xiaoya-teacher-mcp-server/badges/card.svg)](https://glama.ai/mcp/servers/Sav1ouR520/xiaoya-teacher-mcp-server)

Score Badge

Copy to your README.md:

[![xiaoya-teacher-mcp-server MCP server](https://glama.ai/mcp/servers/Sav1ouR520/xiaoya-teacher-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/Sav1ouR520/xiaoya-teacher-mcp-server)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Sav1ouR520/xiaoya-teacher-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server