Memory Bank MCP Server

Overview Schema Related Servers Score Discussions

Server Quality Checklist

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

Latest release: v1.0.0
Disambiguation4/5
Most tools have distinct purposes, but there is some overlap in creative and plan tools that could cause confusion. For example, creative_add_idea and plan_add_task both involve adding items, and creative_update_design and plan_update_tasks both update documents, which might lead to misselection in certain contexts.
Naming Consistency4/5
The naming follows a consistent verb_noun pattern throughout, with clear actions like create, get, list, update, and delete. However, there are minor deviations such as creative_add_idea (adjective_verb_noun) and van_init/van_verify (prefix_verb), which slightly break the pattern but remain readable.
Tool Count3/5
With 29 tools, the count is borderline high for a memory bank server, suggesting potential over-scoping. While it covers various aspects like projects, rules, documents, and tasks, it might feel heavy and could benefit from consolidation to improve usability and reduce complexity.
Completeness5/5
The tool set provides comprehensive coverage for the memory bank domain, including full CRUD operations for projects, rules, and documents, along with specific workflows for planning, creativity, implementation, reflection, and archival. No obvious gaps are present, ensuring agents can handle complete lifecycles without dead ends.
Average 2.4/5 across 29 of 29 tools scored. Lowest: 1.7/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 0 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
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 are provided, so the description carries the full burden of behavioral disclosure. '创建新规则' only indicates a creation action but reveals nothing about required permissions, whether this operation is idempotent, what happens on success/failure, rate limits, or what the response contains. For a mutation tool with zero annotation coverage, this description provides minimal behavioral insight beyond the basic action implied by the name.
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?
While technically concise with just three Chinese characters, this is an example of under-specification rather than effective conciseness. The description doesn't front-load important information or provide any structured explanation. Every sentence should earn its place, but here the single phrase doesn't provide enough value to justify its existence as a helpful description.
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 this is a mutation tool with 5 parameters, no annotations, and no output schema, the description is completely inadequate. It doesn't explain what 'rules' are in this context, what happens after creation, error conditions, or any behavioral aspects. The description fails to compensate for the lack of structured metadata, leaving the agent with minimal guidance for proper tool 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?
The schema has 100% description coverage, with all 5 parameters documented in the schema itself. The description adds no additional parameter information beyond what's already in the structured schema. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no parameter info in the description, which applies here.
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 '创建新规则' (Create new rule) is a tautology that essentially restates the tool name 'create_rule' in Chinese. It doesn't specify what kind of rule this creates (automation rule, business rule, validation rule) or what system/context these rules operate in. While it clearly indicates a creation action, it lacks the specificity needed to distinguish it from other rule-related tools like 'update_rule' or 'delete_rule' beyond the basic verb.
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?
The description provides absolutely no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (like needing a project for non-global rules), when to choose this over 'update_rule', or what happens after creation. With sibling tools like 'delete_rule', 'get_rule', 'list_rules', and 'update_rule' available, the lack of any contextual guidance is a significant omission.
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, so the description carries full burden for behavioral disclosure. '删除规则' only indicates a destructive deletion action but reveals nothing about permissions required, whether deletion is permanent or reversible, side effects (e.g., if related data is cascade-deleted), error handling, or response format. For a mutation tool with zero annotation coverage, this is critically insufficient.
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 two-character phrase ('删除规则'), which is extremely concise but under-specified rather than efficiently informative. It lacks any structure (e.g., no separation of purpose from guidelines) and fails to provide necessary context that would justify its brevity. Conciseness should not come at the cost of clarity.
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 this is a destructive mutation tool with no annotations, no output schema, and a minimal description, the description is completely inadequate. It doesn't address safety concerns, expected outcomes, error conditions, or system-specific behaviors. The agent is left with significant gaps about how to use this tool correctly and what 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% with one parameter ('id' described as '规则ID' - rule ID). The description adds no parameter information beyond what the schema already provides. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even without param details in the description, which applies here.
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 '删除规则' (delete rule) is a tautology that merely restates the tool name in Chinese. It specifies the verb (delete) and resource (rule) but provides no additional context about what a 'rule' represents in this system or what deletion entails. While it distinguishes from some siblings like 'create_rule' or 'update_rule', it doesn't clarify scope or differentiate from other deletion tools like 'delete_project'.
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?
The description offers no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing rule ID), exclusions (e.g., cannot delete active rules), or relationships with sibling tools like 'get_rule' to verify existence first. Without any usage context, an agent must infer everything 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.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. '记录实现细节' gives no indication of whether this is a read or write operation, what permissions are required, whether notes are permanent or editable, or what happens after creation. For a tool that appears to create content (based on name and parameters), this is a critical gap in behavioral transparency.
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?
While technically concise (only 4 Chinese characters), this is a case of under-specification rather than effective conciseness. The description is too brief to be helpful - it doesn't front-load critical information and fails to communicate the tool's purpose effectively. Every sentence should earn its place, but this single phrase doesn't earn its place by providing meaningful guidance.
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?
For a tool with 4 parameters, no annotations, and no output schema, the description is completely inadequate. It doesn't explain what the tool does, when to use it, what behavior to expect, or what the result will be. Given the complexity of the tool (creating notes with project associations and task relationships) and the lack of structured metadata, the description fails to provide the necessary context for an AI agent to use this 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?
The schema description coverage is 100%, with all parameters well-documented in the schema itself. The description adds no additional parameter information beyond what's already in the schema. According to scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description.
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 '记录实现细节' (Record implementation details) is vague and tautological - it essentially restates the tool name 'implement_add_note' without specifying what kind of note is being added or to what system. It doesn't clearly distinguish this from sibling tools like 'creative_add_idea' or 'reflect_create' which also appear to create content items.
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?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, appropriate contexts, or distinctions from similar tools like 'creative_add_idea' or 'reflect_create'. The agent receives no help in determining when this specific note-adding 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?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The description '更新进度文档' implies a write/mutation operation but provides no information about permissions needed, whether changes are reversible, what happens to existing content, rate limits, or what the response looks like. For a mutation tool with zero annotation coverage, this is a critical gap in behavioral transparency.
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?
While the description is extremely concise (only 4 Chinese characters), this represents under-specification rather than effective brevity. The single phrase doesn't provide enough information to be helpful, making it inefficient rather than well-structured. Every sentence should earn its place, but here the minimal content fails to provide necessary context.
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?
For a mutation tool with no annotations and no output schema, the description is completely inadequate. It doesn't explain what the tool actually does beyond the basic verb, doesn't provide usage context, doesn't describe behavioral characteristics, and doesn't compensate for the lack of structured metadata. The description fails to provide the minimal information needed for an agent to use this 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 description coverage is 100%, with both parameters ('projectId' and 'content') having clear descriptions in the schema. The tool description adds no additional information about parameter meaning, format, or constraints beyond what's already in the schema. With complete schema coverage, the baseline score of 3 is appropriate as the description doesn't need to compensate for schema gaps.
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 '更新进度文档' (Update progress document) is a tautology that essentially restates the tool name 'reflect_update_progress'. It doesn't specify what kind of progress document, how it's updated, or what distinguishes it from similar tools like 'implement_update_progress' or 'update_document'. The description lacks a clear verb+resource combination with specific scope.
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?
The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools that might handle progress or document updates (e.g., 'implement_update_progress', 'update_document', 'reflect_get_history'), but the description offers no context about when this specific tool is appropriate, what prerequisites exist, or when to choose other options.
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 provided, the description carries full burden for behavioral disclosure. '删除项目' only indicates a destructive action but reveals nothing about permissions required, whether deletion is permanent or reversible, what happens to associated data, error conditions, or confirmation requirements. For a destructive operation with zero annotation coverage, this is dangerously inadequate.
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?
While technically concise with just two characters, this is under-specification rather than effective brevity. The description fails to provide necessary information about a destructive operation. Every sentence should earn its place, but here the single phrase doesn't earn its place by being informative enough.
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?
For a destructive tool with no annotations and no output schema, the description is completely inadequate. It doesn't explain what 'delete' entails, what gets removed, whether there are confirmation steps, what the response looks like, or error conditions. Given the high-stakes nature of deletion operations, this represents a critical information gap.
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 schema has 100% description coverage with the single parameter 'id' clearly documented as '项目ID' (project ID). The description doesn't add any parameter information beyond what the schema provides, but with only one well-documented parameter and high schema coverage, the baseline is appropriately high. No additional parameter semantics are needed.
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 '删除项目' (delete project) is a tautology that merely restates the tool name in Chinese without adding any meaningful clarification. It doesn't specify what type of project, what system it operates on, or how it differs from related tools like 'archive_export_project' or 'update_project'. While it does contain a verb+resource, it lacks the specificity needed for proper differentiation.
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?
The description provides absolutely no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (like needing project ID), when deletion is appropriate versus archiving (given sibling tools like 'archive_export_project'), or any constraints. This leaves the agent guessing about proper 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, so the description carries the full burden of behavioral disclosure. It only states the action (export) without explaining what happens (e.g., creates a downloadable file, triggers an async process, requires specific permissions, has rate limits, or affects system state). This leaves critical behavioral traits undocumented.
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 phrase ('导出项目文档'), which is concise and front-loaded. However, it's overly terse and under-specified for a tool with two parameters and no annotations, missing necessary details that would justify a higher score for true efficiency.
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 2 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain the export process, output format (beyond parameter hints), error conditions, or how it differs from sibling tools. For a mutation-like tool (implied by 'export'), more context is needed to guide effective use.
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 schema description coverage is 100%, with clear parameter descriptions in Chinese: '导出格式(markdown, html)' for 'format' and '项目ID' for 'projectId'. The tool description adds no additional meaning beyond the schema, such as default behaviors or usage examples. With high schema coverage, a baseline score of 3 is appropriate as the schema handles parameter documentation adequately.
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 '导出项目文档' (export project documents) restates the tool name 'archive_export_project' in different words, making it tautological. It specifies the action (export) and resource (project documents) but lacks specificity about what 'export' entails (e.g., file generation, download link) and doesn't distinguish it from sibling tools like 'get_document' or 'list_documents'.
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 is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., project must exist), exclusions (e.g., cannot export incomplete projects), or compare it to siblings like 'get_document' (for single documents) or 'list_documents' (for listings). The description is too vague to inform usage decisions.
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 provided, the description carries full burden for behavioral disclosure but offers none. It doesn't indicate whether this is a read-only operation, what permissions might be required, whether results are paginated, what format the output takes, or any rate limits. For a list operation tool with zero annotation coverage, this is completely inadequate.
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 at just four Chinese characters. While this represents severe under-specification rather than ideal conciseness, within the dimension of conciseness alone, it's maximally brief with zero wasted words. Every character serves the core purpose statement.
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?
For a tool with 2 parameters, no annotations, and no output schema, the description is completely inadequate. It doesn't explain what 'ideas' are in this context, what the return format looks like, whether this is a filtered view or complete list, or any behavioral characteristics. The agent would struggle to use this tool effectively based solely on this description.
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 fully documents both parameters (projectId and tag). The description adds no additional parameter information beyond what's in the schema - it doesn't explain what constitutes a valid projectId, what tags might be available, or how the filtering works. Baseline 3 is appropriate when the schema does all the work.
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 '获取创意列表' (Get creative list) is a tautology that essentially restates the tool name 'creative_get_ideas' in Chinese. It doesn't specify what kind of ideas, from where, or with what scope. While it includes a verb ('获取' - get) and resource ('创意列表' - creative list), it lacks specificity and doesn't distinguish this tool from potential siblings like 'creative_add_idea' or 'creative_update_design'.
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?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, appropriate contexts, or when other tools like 'creative_add_idea' or filtering through other list tools might be more suitable. The agent receives zero usage direction beyond the tool name itself.
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 the full burden of behavioral disclosure. '更新文档内容' implies a mutation/write operation, but it doesn't disclose any behavioral traits like required permissions, whether the update overwrites or merges content, what happens if the document doesn't exist, rate limits, or what the response looks like. For a mutation tool with zero annotation coverage, 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While the description is extremely concise (just three Chinese characters), this represents under-specification rather than effective conciseness. The single phrase doesn't provide enough information to be helpful, and it's not front-loaded with the most critical information. Every sentence should earn its place, but here there's essentially no sentence at all.
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 this is a mutation tool with no annotations and no output schema, the description is insufficiently complete. The agent needs to understand what 'updating document content' actually means operationally - does it create documents, overwrite existing ones, append content, or something else? Without annotations or output schema, the description should provide more context about the tool's behavior and expected outcomes.
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% description coverage, with all three parameters (content, projectId, type) clearly documented in the schema. The description adds no additional meaning beyond what the schema already provides about these parameters. With complete schema coverage, 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.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '更新文档内容' (Update document content) is a tautology that essentially restates the tool name 'update_document' in Chinese. It doesn't specify what kind of document or what 'content' refers to, nor does it distinguish this tool from sibling tools like 'update_project' or 'update_rule' that also perform updates on 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 Guidelines1/5
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. There are multiple sibling tools that update various resources (e.g., 'update_project', 'update_rule', 'implement_update_context'), but the description offers no context about when this specific document update tool is appropriate versus those other update operations.
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, so the description carries the full burden of behavioral disclosure. The description only states '创建创意记录' (Create creative record), which implies a write/mutation operation but reveals nothing about permissions needed, side effects, error conditions, response format, or any behavioral traits like rate limits or idempotency. For a mutation tool with zero annotation coverage, this is critically 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?
The description is extremely concise at just three characters in Chinese ('创建创意记录'), which translates to 'Create creative record'. It's front-loaded with the core action and resource, with zero wasted words. For a simple creation tool, this brevity is efficient, though it comes 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?
Given the complexity of a mutation tool with no annotations and no output schema, the description is incomplete. It fails to address key contextual aspects: what an 'idea' entails in this system, how it relates to other entities (e.g., projects), what happens after creation, or any error handling. The high schema coverage helps with parameters, but overall context is lacking for safe and effective use.
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% description coverage, with all parameters documented in Chinese (e.g., '创意内容' for content, '项目ID' for projectId). The description adds no additional meaning beyond what the schema provides—it doesn't explain parameter relationships, constraints, or usage examples. With high schema coverage, the baseline score of 3 is appropriate, as the schema does the heavy lifting.
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 '创建创意记录' (Create creative record) is a tautology that essentially restates the tool name 'creative_add_idea' in Chinese. While it indicates a creation action, it lacks specificity about what kind of record is being created or what distinguishes it from other creation tools like 'create_project' or 'reflect_create'. The purpose is vague without additional context about the domain or resource type.
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?
The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools for creation (e.g., 'create_project', 'reflect_create', 'plan_add_task'), but no indication of when this specific tool for adding ideas is appropriate, what prerequisites might exist, or what scenarios it's designed for. This leaves the agent guessing about 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, so the description carries the full burden of behavioral disclosure. The description only states what the tool does ('获取文档内容') without any information about permissions needed, rate limits, what format the content is returned in, whether this is a read-only operation, or any other behavioral characteristics. For a tool with no annotation coverage, this is completely inadequate.
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 at just four Chinese characters ('获取文档内容'). While this represents under-specification rather than ideal conciseness, according to the scoring framework, conciseness is evaluated separately from completeness. The description is front-loaded with the core purpose and contains zero wasted words or redundant information.
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 that there are no annotations and no output schema, the description should provide more context about what this tool returns and how it behaves. The description is a simple statement of purpose without any information about return format, error conditions, or behavioral characteristics. For a tool that presumably returns document content, the lack of output information is a significant gap.
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 schema description coverage is 100%, with both parameters ('projectId' and 'type') having clear descriptions in the schema. The tool description adds no additional parameter information beyond what's already in the schema. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.
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 '获取文档内容' (Get document content) is a tautology that essentially restates the tool name 'get_document' in Chinese. While it does specify a verb ('获取' - get) and resource ('文档内容' - document content), it doesn't distinguish this tool from its sibling 'list_documents' or provide any specific scope or differentiation. The purpose is clear at a basic level but lacks the specificity needed for effective sibling differentiation.
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?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of when to use 'get_document' versus 'list_documents' (which appears to be a sibling tool), no prerequisites, and no context about appropriate use cases. The agent receives no help in selecting between these two document-related 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 are provided, so the description carries the full burden of behavioral disclosure. '更新规则内容' implies a mutation operation but doesn't specify whether this requires authentication, what permissions are needed, whether changes are reversible, or what happens on success/failure. For a write tool with zero annotation coverage, this leaves critical behavioral traits undocumented.
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—a single phrase in Chinese. While this is efficient, it borders on under-specification rather than optimal conciseness. It's front-loaded but lacks the depth needed for a mutation tool. The structure is minimal, with no wasted words, but 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's complexity (a mutation operation with 3 parameters), lack of annotations, and absence of an output schema, the description is incomplete. It doesn't explain what 'updating rule content' entails, what the return value might be, or how it differs from other update tools. For a write tool in a context with multiple siblings, this minimal description fails to provide adequate 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?
The schema description coverage is 100%, with all three parameters ('id', 'content', 'description') clearly documented in the schema. The description adds no additional parameter semantics beyond what the schema provides (e.g., no examples, format details, or constraints). Given the high schema coverage, a baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.
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 '更新规则内容' (update rule content) is a tautology that essentially restates the tool name 'update_rule' in Chinese. While it indicates the action (update) and target (rule content), it doesn't specify what aspect of the rule is being updated or distinguish this tool from its sibling 'update_document' or 'update_project'. It's minimally informative 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 Guidelines1/5
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 doesn't mention prerequisites (e.g., needing a rule ID), differentiate from similar tools like 'update_document' or 'update_project', or indicate when not to use it (e.g., for creating vs. updating rules). With multiple update-related siblings in the list, this absence of context is a significant gap.
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 the full burden of behavioral disclosure. It states 'update', implying a mutation operation, but doesn't disclose any behavioral traits such as permissions required, whether the update is reversible, side effects, or response format. For a mutation tool with zero annotation coverage, this is a significant gap that leaves the agent uninformed about critical operational aspects.
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 with a single phrase, '更新活动上下文文档', which is front-loaded and wastes no words. While it may be under-specified, it earns a high score for conciseness as every word contributes directly to stating the tool's purpose without redundancy or fluff.
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 (a mutation operation with 2 parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what an 'activity context document' is, how the update behaves, or what the tool returns. The agent is left with significant gaps in understanding the tool's full context and expected outcomes.
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 description adds no parameter semantics beyond what the input schema provides. The schema has 100% description coverage with clear documentation for both parameters ('content' and 'projectId'), so the baseline is 3. The tool description doesn't elaborate on parameter meanings, constraints, or usage examples, but the schema adequately covers the essentials.
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 '更新活动上下文文档' (Update activity context document) is a tautology that essentially restates the tool name 'implement_update_context' in Chinese. It specifies the verb 'update' and resource 'activity context document' but lacks specificity about what this document represents or how it differs from similar tools like 'update_document' or 'implement_update_progress'. The purpose is clear at a basic level but doesn't distinguish meaningfully from siblings.
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?
The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools that involve updates or documents (e.g., 'update_document', 'implement_update_progress', 'update_project'), but the description offers no context, prerequisites, or exclusions to help an agent choose appropriately. This leaves the agent guessing based on tool names 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 the full burden of behavioral disclosure. It states 'update' which implies a mutation operation, but doesn't specify whether this requires specific permissions, what happens on success/failure (e.g., overwrites vs. merges), or any side effects (e.g., notifications, history tracking). For a mutation tool with zero annotation coverage, this is a significant gap in 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 extremely concise—a single phrase in Chinese—with zero wasted words. It's front-loaded and to the point, though this brevity contributes to its lack of detail. Every part of the description serves a purpose, even if that purpose is minimal.
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 (a mutation tool with 2 parameters) and the absence of both annotations and an output schema, the description is incomplete. It doesn't explain what the tool returns, how errors are handled, or the operational context (e.g., is this for collaborative planning?). The 100% schema coverage helps with parameters, but overall, the description fails to provide enough context for safe and effective use.
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 both parameters ('content' and 'projectId') documented in the schema. The description doesn't add any meaning beyond the schema—it doesn't explain how 'content' relates to 'task planning document' or provide context for 'projectId'. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but no extra credit is earned.
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 '更新任务规划文档' (Update task planning document) is a tautology that essentially restates the tool name 'plan_update_tasks' in Chinese. It doesn't specify what 'update' means operationally (e.g., modify, append, replace) or clarify the scope of 'task planning document' beyond what's implied by the name. While it identifies a verb and resource, it lacks the specificity needed to distinguish it from siblings like 'update_document' or 'plan_add_task'.
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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., requires an existing document), exclusions, or compare it to related tools such as 'update_document' (which might handle general documents) or 'plan_add_task' (which might add tasks rather than update planning docs). Without this, an agent cannot make informed decisions about tool 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 carries the full burden of behavioral disclosure. '更新项目信息' implies a mutation operation, but it doesn't specify permissions required, whether changes are reversible, rate limits, error conditions, or what happens on success/failure. For a mutation tool with zero annotation coverage, this is a significant gap in behavioral 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 extremely concise with just four Chinese characters ('更新项目信息'), which efficiently conveys the core purpose without any wasted words. It's appropriately sized for what it does convey, though it suffers from under-specification rather than verbosity.
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 this is a mutation tool (updates project information) with no annotations, no output schema, and multiple sibling tools, the description is incomplete. It doesn't explain what 'project information' encompasses, how updates affect existing data, what values are returned, or how it differs from other update tools. The high schema coverage helps with parameters, but overall context is lacking.
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 description doesn't add any parameter semantics beyond what's already in the input schema, which has 100% description coverage (all three parameters are documented in Chinese). Since schema_description_coverage is high (>80%), the baseline score is 3 even without additional param info in the description. The description doesn't compensate but doesn't need to given the schema completeness.
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 '更新项目信息' (Update project information) is a tautology that essentially restates the tool name 'update_project' in Chinese. While it indicates the verb (update) and resource (project information), it lacks specificity about what aspects can be updated and doesn't distinguish this tool from sibling tools like 'update_document' or 'update_rule'.
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?
The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools that perform updates (e.g., update_document, update_rule, creative_update_design), but the description doesn't indicate this is specifically for updating project metadata versus other entities. No prerequisites, exclusions, or context for usage are 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, so the description carries the full burden of behavioral disclosure. It only states the action ('get rule content') without mentioning whether this is a read-only operation, if it requires authentication, what happens on failure (e.g., invalid ruleId), or the format of the returned content. For a tool with no annotation coverage, this leaves critical behavioral traits unspecified.
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 with a single phrase ('获取规则内容'), which is front-loaded and wastes no words. However, it may be overly terse given the lack of other context, bordering on under-specification rather than optimal brevity.
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 (one parameter, no output schema, no annotations), the description is incomplete. It doesn't explain what 'rule content' entails, how it differs from other rule-related tools, or what the output might look like. For a retrieval tool in a context with multiple sibling tools, more guidance is needed to ensure proper agent 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?
The input schema has 100% description coverage (ruleId is documented as '规则ID' or 'rule ID'), so the schema provides complete parameter documentation. The description adds no additional meaning about the parameter beyond what's in the schema, such as format examples or constraints. With high schema coverage, 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.
Purpose2/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取规则内容' (Get rule content) is a tautology that essentially restates the tool name 'get_rule' in Chinese. It doesn't specify what 'rule content' includes or how it differs from sibling tools like 'list_rules' or 'create_rule'. While it indicates a retrieval action, it lacks specificity about the resource being accessed.
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. With sibling tools like 'list_rules' (likely for listing multiple rules) and 'update_rule' (for modifying rules), the description provides no context about whether this tool retrieves a single rule by ID, when it should be preferred over listing, or any prerequisites for 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 carries the full burden of behavioral disclosure. '生成' (generate) implies a creation/write operation, but the description doesn't specify if this requires specific permissions, whether it's idempotent, what format the output takes (e.g., text, PDF), or if it has side effects like updating project status. It lacks details on rate limits, error handling, or response behavior, leaving significant gaps for a tool that likely produces reports.
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, efficient sentence ('生成项目总结报告') that is front-loaded and wastes no words. It's appropriately sized for a simple tool, though it could benefit from more detail given the lack of annotations and output schema. Every word earns its place, but it might be too concise for full clarity.
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 (a report-generation tool with 3 parameters), no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a text summary, a file ID), behavioral traits, or usage context. For a tool that likely involves data processing and output creation, more information is needed to guide an AI agent 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 description coverage is 100%, with all parameters ('projectId', 'title', 'includeSections') documented in the schema. The description adds no additional meaning beyond the schema, such as explaining what 'includeSections' might contain (e.g., typical report sections) or how 'title' is used. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description doesn't compensate or enhance understanding.
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 '生成项目总结报告' (Generate project summary report) states a clear verb ('生成' - generate) and resource ('项目总结报告' - project summary report), but it's somewhat vague about what exactly constitutes a 'summary report' and doesn't differentiate from sibling tools like 'archive_export_project' or 'reflect_create' that might also produce project-related outputs. It avoids tautology since it doesn't just restate the tool 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?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing project), exclusions, or comparisons to siblings like 'archive_export_project' (which might export data) or 'reflect_create' (which might create reflections). Usage is implied only by the tool name and description, with no explicit 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 are provided, so the description carries the full burden of behavioral disclosure. It states it 'gets' a list, implying a read-only operation, but doesn't specify whether it returns all rules or is paginated, what happens if the projectId is invalid, or if authentication is required. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
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, efficient phrase ('获取项目规则列表') that directly states the tool's purpose without unnecessary words. It's front-loaded with the core action. However, it could be slightly more structured by explicitly mentioning it returns a list, but overall it's concise 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 the tool has no annotations, no output schema, and a simple input schema, the description is incomplete. It doesn't explain return values (e.g., list format, rule fields), error conditions, or behavioral details like pagination. For a list operation, this lack of context makes it harder for an agent to use correctly without trial and error.
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 the single parameter 'projectId' documented as '项目ID' (project ID). The description doesn't add any meaning beyond this, such as format examples (e.g., numeric vs. string IDs) or context (e.g., must be an existing project). With high schema coverage, the baseline score of 3 is appropriate as the schema handles parameter documentation adequately.
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 '获取项目规则列表' (Get project rules list) clearly states the verb (get/list) and resource (project rules), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_rule' (which presumably retrieves a single rule) or 'list_documents' (which lists documents instead of rules), leaving some ambiguity about when to use this specific list operation versus other retrieval tools.
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 doesn't mention prerequisites (e.g., needing a valid projectId), exclusions (e.g., not for archived rules), or comparisons to siblings like 'get_rule' for single rule retrieval or 'list_documents' for document listings. The agent must infer usage from the tool name and schema 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?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action ('获取' - get) without detailing return format, pagination, error handling, or whether it's read-only (implied but not explicit). This is inadequate for a tool with behavioral implications.
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, efficient sentence with no wasted words. It's front-loaded with the core action, though it could be more structured by including context or usage hints without sacrificing brevity.
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 (a read operation with one required parameter) and lack of annotations or output schema, the description is incomplete. It doesn't explain what 'current' means, the return format, or how it interacts with siblings, leaving significant gaps for agent 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%, with the parameter 'projectId' documented as '项目ID' (project ID). The description adds no additional meaning beyond the schema, such as explaining what 'current' tasks are relative to the project. Baseline 3 is appropriate as the schema handles parameter documentation.
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 '获取当前任务列表' (Get current task list) states a clear verb ('获取' - get) and resource ('任务列表' - task list), but lacks specificity about scope or filtering. It doesn't distinguish from siblings like 'plan_update_tasks' or 'archive_completed_tasks', making it vague about what 'current' means in context.
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. It doesn't mention prerequisites like requiring a projectId, nor does it differentiate from other task-related tools such as 'plan_add_task' or 'archive_completed_tasks', leaving usage context unclear.
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 the full burden of behavioral disclosure. '创建' (Create) implies a write operation, but it doesn't specify permissions required, whether the creation is idempotent, what happens on failure, or the expected response format. This leaves significant gaps in understanding the tool's behavior 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 a single, efficient sentence in Chinese that directly states the tool's purpose without unnecessary words. It's front-loaded and to the point, though it could be slightly more specific to improve clarity 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 creation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral aspects (e.g., error handling, permissions), usage context, and what the tool returns. Given the complexity of a write operation and the absence of structured data to compensate, the description should provide more comprehensive guidance to be fully 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 schema description coverage is 100%, with clear descriptions for each parameter (e.g., '反思内容' for content, '项目ID' for projectId). The description adds no additional meaning beyond the schema, such as format examples or constraints. Given the high schema coverage, a baseline score of 3 is appropriate as the schema adequately documents the parameters.
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 '创建项目反思记录' (Create project reflection record) states the action and resource clearly, but it's somewhat vague about what a 'reflection record' entails compared to siblings like 'reflect_get_history' or 'reflect_update_progress'. It doesn't specify if this is a journal entry, review, or other type of reflection, leaving room for ambiguity in distinguishing it from related tools.
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 prerequisites (e.g., needing an existing project), exclusions, or how it differs from other 'reflect_' tools like 'reflect_get_history' or 'reflect_update_progress'. The description alone offers no context for selection among 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 provided, the description carries the full burden of behavioral disclosure. It only states the action ('get') without detailing traits like whether it's read-only (implied but not explicit), requires authentication, has rate limits, returns paginated results, or handles errors. For a tool with no annotations, this minimal description fails to provide essential 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence ('获取历史反思记录') that directly states the purpose without unnecessary words. It's appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness. There's no fluff, making it front-loaded and easy to parse.
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 a tool with 2 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral traits, usage guidelines, and what the return values might include (e.g., list of records, format). For a tool in a server with multiple reflection-related siblings, more context is needed to ensure the agent can use it 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?
The schema description coverage is 100%, with clear descriptions for both parameters ('limit' and 'projectId'). The description doesn't add any meaning beyond what the schema provides, such as explaining how parameters interact or their impact on results. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.
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 '获取历史反思记录' (Get historical reflection records) clearly states the verb (get) and resource (historical reflection records), providing a basic purpose. However, it doesn't distinguish this tool from potential siblings like 'reflect_create' or 'reflect_update_progress' that also deal with reflection records, making it vague about its specific role within the reflection domain.
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. The description doesn't mention prerequisites, context, or exclusions, such as whether it's for viewing past reflections versus creating new ones (as with 'reflect_create') or updating them (as with 'reflect_update_progress'). This leaves the agent without direction on appropriate usage scenarios.
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 the full burden. It mentions '检查或创建必要文件', implying a read/write operation that may modify files, but does not disclose behavioral traits like permissions needed, side effects, error handling, or output format. For a tool with no annotations, this is insufficient to inform safe or effective use.
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 in a single sentence, '初始化项目，检查或创建必要文件', with no wasted words. It efficiently states the core action, though it could be slightly more informative. The structure is straightforward, earning a high score for brevity.
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 (initialization with potential file creation), lack of annotations, and no output schema, the description is incomplete. It does not explain what 'necessary files' are, the outcome of initialization, or error conditions. For a tool that may involve mutations, more context is needed to ensure proper use.
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 descriptions for both parameters ('description' and 'projectName'). The description adds no additional meaning beyond the schema, such as explaining parameter interactions or defaults. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description does not compensate but also does not detract.
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 '初始化项目，检查或创建必要文件' states the purpose as initializing a project and checking/creating necessary files, which is clear but vague. It specifies the action ('初始化') and resource ('项目'), but lacks detail on what 'necessary files' entails or how it differs from sibling tools like 'create_project' or 'van_verify', making it moderately clear but not distinct.
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, exclusions, or comparisons to sibling tools such as 'create_project' or 'van_verify', leaving the agent without context for selection. This results in minimal 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?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('归档' - archive) but doesn't explain what 'archive' entails (e.g., moving tasks, marking as archived, deleting, or storing elsewhere), potential side effects, permissions required, or rate limits. This is a significant gap for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient phrase ('归档已完成任务') that is front-loaded and wastes no words. It directly conveys the core action without unnecessary elaboration, making it highly concise and well-structured for its purpose.
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 a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on what archiving entails, behavioral traits, return values, or how it differs from sibling tools. This leaves critical gaps for an agent to understand and invoke the tool 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?
The schema description coverage is 100%, with both parameters ('destination' and 'projectId') documented in the schema. The description adds no additional meaning beyond what the schema provides, such as explaining the relationship between parameters or usage examples. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '归档已完成任务' (Archive completed tasks) clearly states the verb ('归档' - archive) and resource ('已完成任务' - completed tasks), providing a basic purpose. However, it doesn't differentiate from sibling tools like 'archive_export_project' or 'archive_generate_summary', leaving ambiguity about what specifically distinguishes this archiving operation from others.
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. There are no explicit instructions on prerequisites, context, or exclusions, and it doesn't mention sibling tools like 'archive_export_project' or 'archive_generate_summary' that might handle related archiving functions, leaving usage unclear.
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 the full burden of behavioral disclosure. '更新' (update) implies a mutation operation, but the description doesn't specify permissions needed, whether changes are reversible, rate limits, or what happens to existing content. This is a significant gap for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient phrase ('更新系统设计文档') with zero waste. It's appropriately sized and front-loaded, making it easy to parse quickly without unnecessary elaboration.
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 as a mutation operation with no annotations and no output schema, the description is incomplete. It lacks details on behavioral traits, error handling, or return values, which are critical for an agent to use this tool effectively in context with its siblings.
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 description adds no meaning beyond what the input schema provides. With 100% schema description coverage, the schema already documents both parameters ('content' and 'projectId') clearly. The baseline score of 3 is appropriate as the schema does the heavy lifting, but the description doesn't compensate with additional context like format examples or constraints.
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 '更新系统设计文档' (Update system design document) states a clear verb ('更新' - update) and resource ('系统设计文档' - system design document), which is better than a tautology. However, it doesn't distinguish this tool from sibling tools like 'update_document' or 'update_project', making it somewhat vague about its specific scope within the system.
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 doesn't mention prerequisites, exclusions, or compare it to similar tools like 'update_document' or 'creative_add_idea', leaving the agent to guess based on 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. '更新' (update) implies a mutation operation, but the description doesn't disclose any behavioral traits: no mention of permissions needed, whether changes are reversible, what happens on success/failure, rate limits, or side effects. For a mutation tool with zero annotation coverage, 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?
Extremely concise - a single phrase with zero waste. However, this conciseness comes at the cost of completeness. The description is front-loaded but under-specified rather than appropriately sized for the tool's complexity.
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 mutation tool with 4 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what 'development progress' means, what gets updated, what the return values might be, or how this differs from similar update tools. The minimal description fails to provide necessary context for proper tool selection and 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 description coverage is 100%, so the schema already documents all four parameters (completion, projectId, status, taskId) with their types, descriptions, and required status. The description adds no additional parameter semantics beyond what's in the schema. Baseline 3 is appropriate when schema does the heavy lifting.
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 '更新开发进度' (Update development progress) states a clear verb ('更新' - update) and resource ('开发进度' - development progress), but it's vague about scope and doesn't distinguish from siblings like 'implement_update_context' or 'plan_update_tasks'. It doesn't specify whether this updates task progress, project progress, or something else.
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. There are multiple update-related siblings (implement_update_context, plan_update_tasks, reflect_update_progress, update_project, etc.), but the description provides no differentiation. It doesn't mention prerequisites, constraints, or appropriate contexts for use.
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 the full burden of behavioral disclosure. The description only states what the tool does ('get project document list') without mentioning whether it's read-only, paginated, rate-limited, requires authentication, or returns structured data. For a list operation with zero annotation coverage, this is inadequate.
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 phrase ('获取项目文档列表') that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with zero wasted content.
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 (a list operation with one parameter) and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the output looks like (e.g., list format, fields included), error conditions, or behavioral traits. The agent is left guessing about key aspects of the tool's behavior.
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% description coverage, with the single parameter 'projectId' documented as '项目ID' (project ID). The description doesn't add any meaning beyond what the schema provides—it doesn't explain what constitutes a valid project ID or how it relates to the output. With high schema coverage, 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.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取项目文档列表' translates to 'Get project document list', which clearly states the verb ('get') and resource ('project document list'). However, it doesn't distinguish this tool from its sibling 'get_document', which appears to retrieve a single document rather than a list. The purpose is clear but lacks sibling 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 'get_document' or 'list_projects'. It doesn't mention prerequisites, exclusions, or specific contexts where this tool is appropriate. The agent must infer usage 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 the full burden of behavioral disclosure. While '验证' (verify) implies a read-only check, the description doesn't specify whether this tool requires authentication, has rate limits, returns detailed error messages, or what happens if verification fails. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
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 with just one Chinese phrase ('验证项目状态和文件完整性'), which directly states the tool's purpose without any wasted words. It's appropriately sized for a simple verification tool.
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 verifying both 'project status and file integrity', no annotations, no output schema, and a single parameter, the description is incomplete. It doesn't explain what constitutes 'status' or 'integrity', what format the results take, or whether this is a lightweight check versus a comprehensive audit. The description should provide more context for proper tool selection.
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 description adds no parameter semantics beyond what the input schema provides. With 100% schema description coverage (the 'projectId' parameter is documented in the schema), the baseline is 3. The description doesn't explain how the projectId relates to the verification process or provide any additional context about parameter usage.
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 '验证项目状态和文件完整性' (Verify project status and file integrity) states a clear purpose with a specific verb ('验证' - verify) and scope (project status and file integrity). However, it doesn't distinguish this tool from potential sibling tools that might also check status or integrity, and the scope remains somewhat vague about what 'file integrity' entails.
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. With sibling tools like 'get_document', 'list_projects', and 'van_init' that might relate to project or file operations, there's no indication of when 'van_verify' is appropriate or what prerequisites might be needed.
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 the full burden of behavioral disclosure. '创建新项目' implies a write operation but doesn't specify permissions needed, whether the operation is idempotent, what happens on failure, or what the response contains. This is inadequate for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with just three characters in Chinese ('创建新项目'), which translates to 'Create new project'. It's front-loaded and wastes no words, making it efficient for quick 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?
For a creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what a 'project' entails in this context, what happens after creation, or any side effects. Given the complexity of project management implied by sibling tools, more context is needed for effective use.
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 description adds no parameter information beyond what's already in the schema, which has 100% coverage with clear descriptions for both 'name' and 'description'. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, though the description doesn't enhance understanding of parameter usage or constraints.
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 '创建新项目' (Create new project) clearly states the verb ('create') and resource ('project'), making the purpose immediately understandable. However, it doesn't distinguish this tool from similar siblings like 'update_project' or 'delete_project', which would require more specific 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. With siblings like 'update_project', 'delete_project', and 'list_projects' available, there's no indication of prerequisites, appropriate contexts, or when other tools might be more suitable.
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 but offers minimal behavioral insight. It states the action is '添加' (add), implying a write operation, but doesn't disclose permissions needed, whether tasks are editable after creation, how they integrate with projects, or what happens on success/failure. This leaves significant gaps 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 directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with zero wasted content.
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 mutation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after task creation, how tasks relate to projects (via projectId), or potential error conditions. Given the complexity of adding tasks with deadlines and priorities, more context is needed for effective use.
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 in the schema itself. The tool description adds no additional parameter context beyond implying it adds tasks, which is already evident from the name and schema. This 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '添加新任务到任务列表' (Add new task to task list) clearly states the action (add) and resource (task list) in specific terms. It distinguishes from siblings like 'plan_get_tasks' (read) and 'plan_update_tasks' (update), but doesn't explicitly differentiate from other creation tools like 'create_project' or 'creative_add_idea' beyond the 'task' focus.
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. While the name implies it's for adding tasks to a plan, there's no mention of prerequisites, when not to use it, or how it relates to other task management tools like 'plan_update_tasks' or 'implement_update_progress'.
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 the full burden. It states it's a read operation ('获取' - get), but doesn't disclose behavioral traits like pagination, sorting, filtering options, rate limits, or authentication needs. This is a significant gap for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that directly states the tool's purpose without any fluff. It's appropriately sized and front-loaded, making it easy to parse quickly.
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 (0 parameters, no output schema, no annotations), the description is minimally adequate but lacks completeness. It doesn't explain what 'all projects' entails (e.g., archived vs. active), return format, or any constraints, which could hinder effective use despite the low complexity.
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 0 parameters, and schema description coverage is 100%, so there's no need for parameter details in the description. The baseline for 0 parameters is 4, as the description appropriately doesn't add unnecessary information beyond confirming no inputs are required.
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 '获取所有项目列表' (Get all project list) clearly states the verb ('获取' - get) and resource ('项目列表' - project list), making the purpose understandable. However, it doesn't differentiate from potential siblings like 'list_documents' or 'list_rules' beyond the resource name, which prevents a perfect score.
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 doesn't mention prerequisites, exclusions, or compare it to other list operations (e.g., 'list_documents'), leaving the agent to infer usage from the name alone.
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:

[![memory-bank-mcp-server MCP server](https://glama.ai/mcp/servers/yywdandan/memory-bank-mcp-server/badges/card.svg)](https://glama.ai/mcp/servers/yywdandan/memory-bank-mcp-server)

Score Badge

Copy to your README.md:

[![memory-bank-mcp-server MCP server](https://glama.ai/mcp/servers/yywdandan/memory-bank-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/yywdandan/memory-bank-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/yywdandan/memory-bank-mcp-server'

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