Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Symphony of One MCP Create a task in the dev room for the backend agent to review the new API schema."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that enables multiple Claude instances to collaborate through a centralized hub with shared workspace and real-time communication.
User (Orchestrator) ← Central Hub Server → Shared Working Directory
↑ ↓ ↑
Hub CLI Interface Message Router File Access
↑ ↓ ↓
Multiple Claude Code Instances via MCP Servers ← → CollaborationRelated MCP server: Orchestrator MCP Server
server.js)Express + Socket.IO server for agent coordination
Room-based chat system for agent communication
Task management and delegation system
File watching with real-time change notifications
REST API for agent management and orchestration
cli.js)Command & control interface for the user
Agent monitoring and task assignment
Broadcasting messages to agent groups
Real-time system statistics and room management
mcp-server.js)MCP server that Claude Code instances connect to
Shared file system access with security constraints
Real-time chat participation with other agents
Task execution and progress reporting
File change notifications and collaboration sync
npm run setupThis will:
Install all dependencies (including sqlite3)
Create the shared workspace directory
Test the MCP server
Show Claude Desktop configuration instructions
🆕 New in v2.0: Enhanced CLI with role management, task templates, and tab completion!
npm run serverThis starts the hub server on http://localhost:3000 with a shared directory at ./shared
Generate the correct configuration for your environment:
npm run configThis creates:
claude-config-windows.json - For Claude Desktop (Windows)
claude-config-wsl.json - For Claude Code (WSL)
Note: The examples below show placeholder paths. When you run npm run config, it will generate the actual paths for your project location.
Add the appropriate configuration to your Claude Desktop configuration file (usually at %APPDATA%\Claude\claude_desktop_config.json):
For Claude Desktop (Windows):
{
"mcpServers": {
"claude-symphony-of-one": {
"command": "node",
"args": ["C:\\path\\to\\your\\project\\mcp-server-wrapper.js"],
"env": {
"CHAT_SERVER_URL": "http://localhost:3000",
"SHARED_DIR": "C:\\path\\to\\your\\project\\shared",
"AGENT_NAME": "Claude-Agent-Windows"
}
}
}
}For Claude Code (WSL):
{
"mcpServers": {
"claude-symphony-of-one": {
"command": "node",
"args": ["/mnt/c/path/to/your/project/mcp-server-wrapper.js"],
"env": {
"CHAT_SERVER_URL": "http://localhost:3000",
"SHARED_DIR": "/mnt/c/path/to/your/project/shared",
"AGENT_NAME": "Claude-Agent-WSL"
}
}
}
}🔧 Note: The configurations use the smart wrapper script (mcp-server-wrapper.js) which automatically handles Windows/WSL path differences.
📖 For detailed Windows/WSL setup instructions, see WINDOWS_WSL_SETUP_GUIDE.md
npm run cliThis opens the orchestrator interface for managing agents and tasks.
Restart Claude Desktop to load the MCP server. You should now see the Symphony of One tools available in Claude.
CHAT_SERVER_URL: Hub server URL (default: http://localhost:3000)
SHARED_DIR: Shared workspace directory (default: ./shared)
AGENT_NAME: Agent display name (default: auto-generated)
PORT: Hub server port (default: 3000)
If you prefer manual setup, see the claude-config-example.json file for the exact configuration format.
npm testThis will test the MCP server functionality and verify all tools are working correctly.
room_join - Join a chat room for collaboration
send_message - Send messages to other agents (supports @mentions)
get_messages - Get conversation history
room_leave - Leave current room
task_create - Create tasks for agent coordination
task_list - View all room tasks
Task assignment and status tracking
file_read - Read files from shared directory
file_write - Write files to shared directory
file_list - List directory contents
file_delete - Remove files
Automatic change notifications to all agents
memory_store - Store persistent information with optional expiration
memory_retrieve - Retrieve stored memories by key or type
notifications_get - Get mentions and alerts for this agent
notification_read - Mark notifications as read
/role assign - Interactive role assignment with guided menus
/role list - Show current agent role assignments
/roles - List all available predefined roles
/role create - Create custom organizational roles
/role prompt <agent> - Send role-specific instructions
/template list - Show available task templates
/template use <name> - Create tasks from templates with variables
/quick bug - Emergency bug fix assignment
/quick security - Security incident response
/quick feature - New feature development
/quick performance - Performance optimization
/quick review - Code review request
/join <room> - Join/create a room (with TAB completion)
/rooms - List all rooms
/agents - Show agents in current room with role info
/history [n] - Show recent messages
/broadcast <msg> - Send message to all agents
/assign <agent> <task> - Assign task to specific agent
/tag <agent> <msg> - Send tagged message to specific agent (@mention)
/monitor [room] - Monitor room activity
/stats - Show system statistics
/task create - Create new tasks
/task list - View all tasks
/task update <id> - Update task status
TAB key - Auto-complete commands and parameters
UP/DOWN arrows - Navigate command history
Interactive menus - Use arrow keys for selections
/clear - Clear screen and show quick start guide
/memory list - View system memory usage
/notifications - View recent notifications and mentions
/logs [type] - View system activity logs
Multiple Claude instances work on different parts of a codebase
Real-time file change notifications keep all agents synchronized
Task delegation and progress tracking
Shared workspace prevents conflicts
Agents can specialize in different analysis domains
Chat-based coordination for complex problem solving
Shared document editing and review
Task assignment based on agent capabilities
User defines high-level goals and delegates to agents
Agents self-coordinate through chat and task system
File-based deliverable sharing and review
Progress monitoring and intervention capabilities
POST /api/join/:room - Agent joins room
POST /api/send - Send chat message
GET /api/messages/:room - Get message history
GET /api/rooms - List all rooms
POST /api/tasks - Create task
GET /api/tasks/:room - Get room tasks
POST /api/tasks/:id/update - Update task
POST /api/memory/:agentId - Store agent memory
GET /api/memory/:agentId - Retrieve agent memory
GET /api/notifications/:agentId - Get agent notifications
POST /api/notifications/:id/read - Mark notification as read
GET /api/stats - System statistics
POST /api/broadcast/:room - Broadcast message
GET /api/agents/:room - List room agents
Predefined Agent Roles: 11 specialized roles across Development, Analysis, Management, Quality, Operations, Documentation, and Research
Interactive Role Assignment: Use /role assign to assign roles to agents with guided menus
Task Templates: 7+ predefined templates for common workflows (code review, feature implementation, bug fixes, etc.)
Quick Assignments: Instant task creation with /quick bug, /quick security, etc. that auto-suggest appropriate agents
Tab Completion: IntelliSense-like command completion with TAB key
Custom Roles & Templates: Create organization-specific roles and task templates
Use @agentName in messages to tag specific agents
Tagged agents receive real-time notifications
Orchestrator can use /tag <agent> <message> for direct communication
Persistent notification storage and management
SQLite database for all messages, tasks, and agent data
Agent memory system with optional expiration
Persistent notification system with read/unread status
Comprehensive logging with Winston
Data survives server restarts
Real-time activity monitoring
Persistent message and event logging
System statistics and memory usage tracking
Agent activity and performance metrics
Path traversal protection for file operations
Sandboxed shared directory access
Agent capability declarations and validation
WebSocket authentication and room isolation
Secure memory storage with expiration
Audit trail for all agent actions
Agent authentication and permissions
File locking for concurrent access
Task dependencies and workflows
Agent discovery and capability matching
Advanced monitoring and analytics
Memory cleanup and optimization
Notification channels and routing
Create a new task for coordination
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Task title | |
| description | Yes | Task description | |
| assignee | No | Agent to assign to | |
| priority | No | Task priority (default: medium) |
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 'Create' implies a write/mutation operation, the description doesn't disclose important behavioral traits like whether this requires specific permissions, what happens on success/failure, whether tasks are persistent, or any rate limits. 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at just 5 words ('Create a new task for coordination'). It's front-loaded with the core purpose and wastes no words. Every word earns its place, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given this is a mutation tool (creating tasks) with no annotations, no output schema, and 4 parameters, the description is insufficiently complete. It doesn't explain what happens after creation, what format the task takes, whether there are side effects, or how this integrates with the coordination context. The description should do more to compensate for the lack of structured metadata.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 4 parameters with their types, descriptions, enums, and requirements. The description adds no additional parameter information beyond what's in the schema. According to the 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create a new task') and the resource ('for coordination'), which provides a specific verb+resource combination. However, it doesn't distinguish this tool from potential sibling tools like 'get_tasks' or other task-related operations that might exist in the future, though among current siblings it's clearly the only task creation tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites, when not to use it, or how it differs from other task management approaches. With sibling tools like 'get_tasks' and 'send_message' available, some context about coordination versus communication would be helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List files in the shared workspace directory
| Name | Required | Description | Default |
|---|---|---|---|
| subdirectory | No | Subdirectory to list (optional) |
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 the action but lacks details on permissions, rate limits, pagination, or return format. For a read operation with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., file names, metadata, errors) or behavioral aspects like access controls. For a tool with no structured data support, more context is needed to fully understand its operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the optional 'subdirectory' parameter. The description implies listing files in a directory but doesn't add syntax or format details beyond what the schema provides. With high schema coverage, a baseline score of 3 is appropriate as the description adds minimal value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('List') and resource ('files in the shared workspace directory'), making the purpose immediately understandable. It doesn't explicitly differentiate from siblings like 'file_read' or 'file_write', but the action is distinct enough to imply listing versus reading/writing content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention siblings like 'file_read' for accessing file contents or 'file_write' for modifying files, nor does it specify prerequisites or contexts for listing files, leaving usage decisions ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a file from the shared workspace
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | Name of the file to read |
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 tool reads a file but doesn't describe what happens on errors (e.g., file not found), the format of returned content, or any limitations like file size constraints. This is a significant gap for a tool that could fail or have hidden behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with zero wasted words. It's front-loaded with the core purpose and appropriately sized for a simple tool, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., file content as text/binary), error conditions, or operational constraints. For a file I/O tool, this leaves critical context gaps that could lead to incorrect usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'filename' parameter clearly documented. The description adds no additional parameter semantics beyond what the schema provides, such as path formats or supported file types. This meets the baseline score of 3 since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Read') and resource ('a file from the shared workspace'), making the tool's purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like file_list or file_write, which would require mentioning it retrieves file contents rather than metadata or performing write operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose file_read over file_list (for listing files) or file_write (for writing files), nor does it specify prerequisites like file existence or permissions. This leaves the agent without contextual usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Write content to a file in the shared workspace
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | Name of the file to write | |
| content | Yes | Content to write to the file |
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 'Write content to a file' implies a mutation operation, it lacks critical details: whether this overwrites existing files or creates new ones, what happens on errors (e.g., permission denied), if there are rate limits, or what the response looks like. For a write 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it easy to parse. Every word earns its place by conveying essential information about the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain behavioral traits (overwrite vs. create, error handling), return values, or usage context. Given the complexity of file operations and the lack of structured data, the description should provide more guidance to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters (filename and content) clearly documented in the schema. The description adds no additional semantic context beyond what the schema provides (e.g., file path conventions, content encoding, or size limits). 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Write content') and target resource ('to a file in the shared workspace'), making the tool's purpose immediately understandable. It distinguishes itself from sibling tools like file_read (read operation) and file_list (listing operation). However, it doesn't specify whether this overwrites existing files or creates new ones, which would make it more specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., file permissions), when not to use it (e.g., for appending vs. overwriting), or how it relates to siblings like file_read or create_task. 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.
Get recent messages from current room
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ISO timestamp to get messages after | |
| limit | No | Maximum number of messages (default: 50) |
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 it 'Get[s] recent messages' but doesn't clarify if this is read-only, what permissions are needed, how pagination works, or what the return format is. This leaves significant gaps for a tool that likely involves data retrieval.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste—it directly states the tool's function without unnecessary words. 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't address behavioral aspects like read-only status, error handling, or return values, which are crucial for a tool that retrieves data. The high schema coverage doesn't compensate for these missing contextual elements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, fully documenting the 'since' and 'limit' parameters. The description adds no additional parameter semantics beyond what the schema provides, such as format details or usage examples, so it meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('recent messages from current room'), making the purpose immediately understandable. However, it doesn't differentiate from potential sibling tools like 'get_notifications' or 'send_message' that might also involve messages, missing full sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'get_notifications' or 'memory_retrieve', nor does it mention any prerequisites or exclusions. It implies usage in the 'current room' context but lacks explicit when/when-not instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get your notifications and mentions
| Name | Required | Description | Default |
|---|---|---|---|
| unreadOnly | No | Only return unread notifications | |
| type | No | Filter by notification type |
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 mentions retrieving notifications and mentions but lacks details on permissions, rate limits, pagination, or response format. This is insufficient for a tool with potential complexity in data retrieval.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with just one short sentence, making it front-loaded and efficient. Every word contributes to the purpose without any waste, earning a perfect score for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete. It doesn't cover behavioral aspects like how results are returned, error handling, or authentication needs, which are crucial for an agent to use the tool effectively in a notification system.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters. The description doesn't add any meaning beyond the schema, such as explaining how parameters interact or default behaviors. Baseline 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'notifications and mentions', making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_messages' or 'get_tasks', which also retrieve information, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_messages' or 'get_tasks'. The description only states what it does without context or exclusions, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get tasks assigned to you or in the room
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Filter by status | |
| assignee | No | Filter by assignee (defaults to you) | |
| priority | No | Filter by priority |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states what the tool does without disclosing behavioral traits like permissions needed, whether it's read-only, pagination, rate limits, or error handling. It mentions scope but lacks operational details crucial for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste, front-loading the core purpose. It's appropriately sized for a simple retrieval tool, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete for a tool with 3 parameters and filtering logic. It doesn't explain return values, error cases, or behavioral constraints, leaving gaps that could hinder an agent's effective use despite the concise purpose statement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional meaning beyond implying filtering by assignee and room context, but doesn't clarify parameter interactions or defaults beyond the schema's 'assignee' description. Baseline 3 is appropriate as schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'tasks' with scope 'assigned to you or in the room', which is specific and actionable. However, it doesn't explicitly differentiate from sibling tools like 'get_messages' or 'get_notifications' beyond the resource type, missing explicit sibling comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides minimal context by mentioning 'assigned to you or in the room', but offers no explicit guidance on when to use this tool versus alternatives like 'get_messages' or 'create_task', nor any prerequisites or exclusions. It lacks clear usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve information from persistent memory
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | Memory key (optional, returns all if not specified) | |
| type | No | Filter by memory type |
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. It states 'Retrieve information from persistent memory', which implies a read-only operation, but doesn't clarify permissions, rate limits, or what 'persistent memory' entails (e.g., is it user-specific, shared, or session-based?). The description lacks details on return format, error handling, or any constraints 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Retrieve information from persistent memory'. It's front-loaded with the core action and resource, with zero wasted words. Every part of the sentence contributes to understanding the tool's purpose, making it appropriately concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (a retrieval tool with 2 parameters), no annotations, and no output schema, the description is incomplete. It doesn't explain what 'persistent memory' means, how results are returned, or any behavioral traits. For a tool that interacts with memory storage, more context is needed to guide effective use, especially without structured output information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters ('key' and 'type') fully documented in the schema. The description adds no parameter-specific information beyond what's in the schema, such as examples or usage context. 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Retrieve' and resource 'information from persistent memory', making the purpose understandable. However, it doesn't distinguish this from sibling tools like 'memory_store' or 'file_read', which could also retrieve information from different sources. The title 'Retrieve Memory' is slightly tautological with the description, but the description adds the 'persistent memory' context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'memory_store' (for storing), 'file_read' (for reading files), or 'get_messages' (for retrieving messages), leaving the agent without context for tool selection. There are no explicit when/when-not statements or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Store information in persistent memory
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Memory key | |
| value | Yes | Memory value | |
| type | No | Memory type (e.g., note, context, learning) | |
| expiresIn | No | Expiration time in seconds (optional) |
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 'Store information in persistent memory', implying a write operation, but doesn't cover permissions, rate limits, error handling, or what 'persistent' entails (e.g., durability, storage 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Store information in persistent memory'. It's front-loaded with the core action and resource, with no wasted words or unnecessary details, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity as a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., permissions, side effects), usage context, and return values, making it inadequate for safe and effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters (key, value, type, expiresIn). The description doesn't add any meaning beyond what the schema provides, such as explaining how 'type' affects storage or what 'expiresIn' defaults to. 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Store information in persistent memory' clearly states the verb ('Store') and resource ('information in persistent memory'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'memory_retrieve' or 'file_write', which would require mentioning it's specifically for memory storage versus retrieval or file operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'memory_retrieve' for retrieval, 'file_write' for file storage, or other memory-related operations, nor does it specify prerequisites or contexts for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Join a chat room to collaborate with other agents
| Name | Required | Description | Default |
|---|---|---|---|
| roomName | Yes | Name of the room to join | |
| agentName | No | Your agent name (optional) | |
| capabilities | No | Your capabilities and role |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions collaboration but doesn't describe what 'join' entails operationally - whether it's a one-time action, establishes a session, requires authentication, has rate limits, or what happens on success/failure. For a tool with no 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core purpose without unnecessary elaboration. It's appropriately sized for the tool's complexity and front-loads the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after joining, what capabilities are needed, whether joining is reversible, or what the expected outcome is. Given the complexity implied by the capabilities parameter and the lack of structured metadata, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no parameter-specific information beyond what's in the schema. The baseline score of 3 reflects adequate coverage through the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('join') and resource ('chat room'), and specifies the purpose ('to collaborate with other agents'). It doesn't differentiate from sibling tools like 'room_leave' or 'send_message', but the verb+resource combination is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives like 'send_message' or 'get_messages', nor about prerequisites or timing. The description only states the basic purpose without contextual usage information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Leave the current chat room
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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. While 'Leave' implies a mutation action, it doesn't specify whether this requires permissions, what happens to messages/notifications after leaving, if the action is reversible, or any rate limits. The description states only the basic action without 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states exactly what the tool does with zero wasted words. It's appropriately sized for a simple action tool and front-loads the core functionality immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is insufficiently complete. It doesn't address what the tool returns, error conditions, side effects, or relationship to sibling tools. While concise, it leaves critical behavioral and contextual gaps that the agent would need to discover through trial and error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the parameter situation. The description appropriately doesn't discuss parameters since none exist, earning a baseline score of 4 for not adding unnecessary information while matching the schema's completeness.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Leave') and resource ('the current chat room'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'room_join' beyond the obvious verb difference, missing an opportunity to clarify the relationship between these room management tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., must be in a room first), consequences of leaving, or when to choose this over other room-related actions. The agent must infer usage context entirely from the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a message to all agents in the current room (supports @mentions)
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | Message content | |
| metadata | No | Optional metadata |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions '@mentions support' which adds some context, but fails to cover critical aspects: whether this is a broadcast (to 'all agents'), potential rate limits, authentication needs, error conditions, or what happens on success. For a mutation tool 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core functionality. It avoids unnecessary words, though it could be slightly more structured by separating core action from features.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks behavioral details (e.g., broadcast nature, side effects), error handling, and response format. The '@mentions support' hint is useful but insufficient given the tool's complexity and lack of structured metadata.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents both parameters (content and metadata). The description adds no parameter-specific information beyond what's in the schema. The baseline score of 3 reflects adequate coverage by the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('send a message') and target ('to all agents in the current room'), with the added feature of '@mentions support'. It distinguishes from siblings like get_messages (read) and room_join/leave (room management), but doesn't explicitly contrast with potential alternatives for sending messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., being in a room), exclusions, or compare with other communication methods. The context is implied ('current room') but lacks explicit usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose with no overlap. For example, file operations (list, read, write) are separate from task management (create, get), messaging (send, get), memory (store, retrieve), and room management (join, leave). The descriptions reinforce unique functions, making misselection unlikely.
Most tools follow a consistent verb_noun pattern (e.g., create_task, file_list, get_messages), but there are minor deviations like 'file_read' and 'file_write' instead of 'read_file' and 'write_file' to align with 'file_list'. This slight inconsistency is readable and doesn't hinder usability.
With 12 tools, the count is well-scoped for a collaboration server covering file management, task coordination, messaging, memory, and room operations. Each tool earns its place by addressing a specific need without bloat, fitting typical ranges for such domains.
The tool set provides complete coverage for agent collaboration: CRUD for files (list, read, write), tasks (create, get), messages (send, get), memory (store, retrieve), and room lifecycle (join, leave). Notifications are included, and there are no obvious gaps that would cause agent failures in this domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ai-wes/claude-symphony-of-one-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
