AI Collaboration MCP Server
Click on "Deploy 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., "@AI Collaboration MCP Serverinitialize project with Gemini as CTO and start the autonomous loop"
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.
AI Collaboration MCP Server
π§ Work in Progress - Active Development π§
A Model Context Protocol (MCP) server designed to facilitate direct AI-to-AI collaboration between Claude and Gemini, eliminating the need for human intermediation in development workflows.
Note: This project is under active development. While core features are functional, some aspects are still being refined. Contributions and feedback are welcome!
π― Project Goal
Enable truly autonomous AI-to-AI collaboration where:
AI agents work continuously on complex projects
Human intervention is minimal (ideally just starting the process)
Agents create comprehensive project plans and execute 100+ phases autonomously
Work continues until project completion or critical blocker
Related MCP server: Gemini Collaboration MCP Server
π Quick Start
Both AIs just run:
@ai-collab init {"agentName": "gemini", "autonomous": true} // For Gemini (CTO)
@ai-collab init {"agentName": "claude", "autonomous": true} // For Claude (Developer)That's it! The init command:
Loads existing project context and state
Creates or resumes a comprehensive project plan
Automatically detects and continues pending work
Shows critical tickets and blockers
Starts autonomous execution loops
π Recent Enhancements
Workflow Optimization (v2.0) π
Task Dependencies: Define
dependsOnrelationships between tasksBatch Task Creation: CTO can create multiple tasks in one command
Priority-Based Work: Tasks are automatically prioritized (high/medium/low)
Continuous Developer Mode: No waiting between tasks - automatic progression
Smart Task Status:
available,blocked,in_progress,in_review,completedDependency Resolution: Tasks automatically unblock when dependencies complete
Autonomous Loop System
120-second check intervals for more natural workflow pacing
500 iteration maximum for extended autonomous operation
Continuous work mode - agents keep working until project completion
Manual loop execution - requires human to run check commands (automation WIP)
Project Plan Management
Auto-generated 6-phase plans from PROJECT_REQUIREMENTS.md
Smart phase progression - automatically moves to next phase when complete
Duplicate task detection - prevents recreating completed features
Ad-hoc mission support - pause main plan for urgent tasks
Enhanced Validation
Ticket vs Task distinction - prevents confusion between bug reports and work items
Role-based instructions - clearer guidance for CTO vs Developer roles
Workflow enforcement - ensures proper task creation and submission flow
β οΈ Current Limitations
Automation Challenges
Manual loop execution required - AI agents can't schedule their own checks
PATH configuration needed - Claude/Gemini commands must be accessible
API quota limits - Gemini has daily request limits that may be exceeded
Addressed Issues β
Single task queuingβ Now supports batch task creationDeveloper idle timeβ Continuous work mode implementedNo task dependenciesβ Full dependency system addedRandom task orderβ Priority-based scheduling active
Remaining Challenges
Agents occasionally create duplicate tasks (improved but not eliminated)
Edit button functionality may need manual verification
Loop execution still requires human intervention
Workarounds Available
Automation scripts provided (
mcp-automator.js) but require setupManual loop execution instructions included
Simulation mode for tracking when automation fails
Features
Core Capabilities
Comprehensive Project Plans: 100+ phase autonomous execution capability
One-Command Startup: Just
initwith autonomous flagRole-Based System: CTO, Developer, PM, QA, Architect roles
Smart Task Management: Duplicate detection and phase progression
Ticketing System: Track bugs, enhancements, tech debt
Context Retention: Maintains state across sessions
Mission Management: High-level objectives with auto-decomposition
Code Review Workflow: Submit, review, and revision cycles
Question & Answer System: Asynchronous clarifications
Comprehensive Logging: Full audit trail
π Enhanced Workflow Features (v2.0)
Task Dependencies: Tasks can depend on other tasks with automatic blocking/unblocking
Priority-Based Scheduling: High/medium/low priority with smart task selection
Batch Task Creation: CTO can queue multiple tasks at once for efficiency
Continuous Work Mode: Developer automatically moves to next available task
Smart Status System:
available,blocked,in_progress,in_review,completedDependency Visualization: Clear indication of task dependencies and blockers
Installation
Clone this repository:
git clone https://github.com/yourusername/ai-collab-mcp.git
cd ai-collab-mcpInstall dependencies:
npm installMake the server executable:
chmod +x src/index.jsConfiguration
For Claude Code
Create a .mcp.json file in your project root:
{
"mcpServers": {
"ai-collab": {
"command": "node",
"args": [".mcp-server/src/index.js"],
"cwd": "/path/to/your/project"
}
}
}For Gemini
Configure in ~/.gemini/settings.json:
{
"mcpServers": {
"ai-collab": {
"command": "node",
"args": ["/path/to/ai-collab-mcp/src/index.js"]
}
}
}Note: Gemini may require explicit instructions to execute MCP commands.
Usage
π― Autonomous Mode (Recommended)
Start with autonomous flag for continuous operation:
# Terminal 1 - Claude (Developer)
@ai-collab init {"agentName": "claude", "autonomous": true}
# Terminal 2 - Gemini (CTO)
@ai-collab init {"agentName": "gemini", "autonomous": true}
# Terminal 3 - Manual Loop Execution (Required)
# Every 120 seconds, run:
@ai-collab get_loop_status {"agentName": "claude"}
@ai-collab get_loop_status {"agentName": "gemini"}Automation Helpers (Experimental)
For reduced manual intervention:
# Run automation script (requires setup)
cd /path/to/project
node mcp-automator.js auto
# Or simulation mode (shows what would happen)
node mcp-automator-v2.js autoSee AUTOMATION.md for setup details.
Traditional Commands
CTO Tools
send_directive- Create development tasks (now with dependencies & priority)send_batch_directives- Create multiple tasks at oncereview_work- Review submissionscreate_project_plan- Start comprehensive planupdate_plan_progress- Move to next phase
Developer Tools
get_all_tasks- View assigned work (sorted by priority)submit_work- Submit completed tasksask_question- Request clarification
π Enhanced Workflow Examples
Creating Tasks with Dependencies
// Single task with dependency
@ai-collab send_directive {
"taskId": "KAN-002",
"title": "Create database tables",
"specification": "Create user and project tables",
"priority": "high",
"dependsOn": ["KAN-001"] // Won't be available until KAN-001 is approved
}
// Batch creation with dependencies
@ai-collab send_batch_directives {
"tasks": [
{
"taskId": "KAN-003",
"title": "Setup database connection",
"specification": "Configure PostgreSQL connection",
"priority": "high"
},
{
"taskId": "KAN-004",
"title": "Create user model",
"specification": "Implement User model with validation",
"priority": "medium",
"dependsOn": ["KAN-003"]
},
{
"taskId": "KAN-005",
"title": "Create auth endpoints",
"specification": "Implement login/register endpoints",
"priority": "medium",
"dependsOn": ["KAN-004"]
}
]
}Continuous Work Mode (Developer)
When the developer runs get_loop_status, they will:
See prioritized available tasks
Automatically start on the highest priority task
After submitting, immediately move to next task
Continue until all available tasks are complete
No more waiting between tasks! The developer keeps working continuously.
Project Plan Workflow
Automatic Plan Creation: On first init, generates 6-phase plan from requirements
Phase Progression: Automatically advances when all phase tasks complete
Duplicate Prevention: Skips tasks that match completed work
Ad-hoc Missions: Can pause main plan for urgent work
Example phases:
Foundation & Basic Structure
Core Interactive Features
UI/UX Enhancement
Data Persistence
Advanced Features
Polish & Quality Assurance
Data Storage
data/
βββ tasks.json # Task tracking
βββ missions.json # Active missions
βββ project-state.json # Project configuration
βββ project-plans.json # Comprehensive plans (NEW)
βββ loop-states.json # Autonomous loop tracking (NEW)
βββ tickets/
βββ tickets.json # Bug/enhancement trackingTroubleshooting
Gemini Not Executing Commands
Prefix with: "Execute the following MCP command:"
Or: "Use the ai-collab tool to run:"
Duplicate Task Creation
System now detects similar task names
Manually clean duplicates from
data/tasks.jsonif needed
Loop Not Continuing
Ensure 120-second intervals between checks
Verify agent hasn't exceeded maxIterations (500)
Check API quotas haven't been exceeded
Contributing
This project needs help with:
True automation (removing manual loop execution)
Better Gemini CLI integration
Improved duplicate detection algorithms
Cross-platform automation scripts
Fork the repository
Create feature branch (
git checkout -b feature/improvement)Commit changes (
git commit -m 'Add improvement')Push branch (
git push origin feature/improvement)Open Pull Request
Roadmap
Native scheduling in MCP server
WebSocket/SSE for real-time updates
Improved role switching
Better error recovery
Multi-project support
Visual progress dashboard
License
MIT License - see LICENSE file for details.
Support
For issues, questions, or contributions, please open an issue on GitHub.
Remember: This is an experimental project pushing the boundaries of AI collaboration. Expect rough edges but exciting possibilities!
Available Tools
28 toolsanswer_questionB
Answer a previously asked question
| Name | Required | Description | Default |
|---|---|---|---|
| answer | Yes | The answer to the question | |
| questionId | Yes | ID of the question being answered |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description only states action without any behavioral details (e.g., side effects, permissions, idempotency).
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?
Extremely brief (4 words), sacrificing necessary context; under-specification rather than conciseness.
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?
Missing output schema and behavioral details; fails to explain return value, errors, or prerequisites.
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 covers 100% of parameters with descriptions; description adds no extra value beyond schema.
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?
Description uses specific verb 'answer' with resource 'question', clearly distinguishing from sibling 'ask_question'.
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?
Implies using after a question is asked, but no explicit conditions or alternatives provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
ask_questionC
Ask a question about a task
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | Task ID the question relates to | |
| context | No | Additional context for the question | |
| question | Yes | The question being asked |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior but only states the basic action. No information on side effects, authorization needs, return format, or interactions with other tools.
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 sentence, achieving conciseness and front-loading the purpose. It is efficient but could be slightly more informative without losing 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 the complexity of 3 parameters, including a nested object, and no output schema, the description is insufficient. It does not explain response format, constraints, or usage flow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter described. However, the description adds no additional meaning beyond the schema. 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 'Ask a question about a task', specifying the verb and resource. However, it does not differentiate from sibling 'answer_question' or other query tools, missing an opportunity to clarify its unique role.
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 'answer_question' or 'diagnose_tasks'. There is no mention of context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_missionC
Create a new mission
| Name | Required | Description | Default |
|---|---|---|---|
| mission | Yes | Mission details | |
| agentName | Yes | Agent creating the mission |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description only states that it creates a mission. It does not disclose side effects, required permissions, or any constraints on the mission object. The nondescript 'Mission details' parameter adds no behavioral insight.
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 very concise (one short sentence), but it sacrifices helpfulness. It could include more context without being verbose, such as typical usage or a link to mission structure.
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 does not explain what a mission is, what happens upon creation, or how to interpret the response. The nested object parameter further demands more detail.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond what the schema provides. The nested 'mission' object is opaque, but the schema already describes both parameters minimally.
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 'Create a new mission' clearly states the action and resource, but it does not distinguish this tool from siblings like 'create_project_plan' or 'create_ticket', leaving ambiguity about what a mission specifically is.
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 (e.g., create_project_plan, create_ticket). The description offers no context about prerequisites or scenarios for creation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_project_planB
Create a comprehensive project plan with multiple phases
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Title of the project plan | |
| description | No | Description of the project | |
| autoGenerate | No | Auto-generate phases from requirements | |
| requirementsPath | No | Path to requirements file (optional) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the tool is destructive, requires authentication, or what side effects occur. This is a significant gap for a creation tool, scoring a 2.
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, concise sentence with no extraneous information. It is front-loaded with the core purpose, earning a 5.
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?
Despite having 4 parameters and no output schema, the description is minimal. It does not explain what 'comprehensive' entails, how phases are auto-generated, or the expected outcome, leaving it incomplete for effective 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?
The input schema already describes all 4 parameters with 100% coverage. The description adds no additional meaning beyond the schema; thus, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a project plan, with a specific focus on 'multiple phases', which distinguishes it from related tools like get_project_plan. It uses a specific verb ('create') and resource ('project plan'), scoring a 5.
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 create_mission or create_ticket. The description lacks context for decision-making, resulting in a score of 2.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_ticketC
Create a new ticket
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Ticket data | |
| type | Yes | Type of ticket | |
| agentName | Yes | Agent creating the ticket |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only states the action without any behavioral details such as side effects, return values, or required permissions. For a creation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but overly minimal. It lacks structure and important details.
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?
The description is incomplete given the tool complexity (3 params, nested object, no output schema). It does not explain the structure of 'data' or what the tool returns.
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%, providing basic descriptions for each parameter. The tool description adds no additional semantics beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new ticket' clearly states the verb and resource, but does not differentiate from sibling tools like update_ticket or list_tickets. However, the name itself 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 on when to use this tool vs alternatives (e.g., update_ticket). No context about prerequisites or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
diagnose_tasksB
Diagnose task state discrepancies between project state and actual tasks
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It only states 'diagnose' without clarifying if it modifies state, is read-only, or what the output format is. An agent cannot infer side effects or safety profile.
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 concise sentence. It is front-loaded with the action, but could be more structured by including return value or side effects without increasing length significantly.
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 output schema and no annotations, the description is insufficient. It does not explain what the diagnostic output looks like (e.g., whether it produces a report, logs, or modifies tasks). The tool name implies a potentially complex analysis, but the description lacks completeness.
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 zero parameters, so the description does not need to add parameter details. Baseline score of 4 applies as there is no missing parameter information.
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 verb 'diagnose' and resource 'task state discrepancies' clearly indicate the tool's purpose of identifying inconsistencies. It is distinct from siblings like get_all_tasks or get_project_state, which only retrieve data. However, the term 'diagnose' could be more specific (e.g., 'generate a report of discrepancies').
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 manually comparing get_project_state and get_all_tasks. The description does not specify prerequisites or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate_context_summaryC
Generate a summary of current project context
| Name | Required | Description | Default |
|---|---|---|---|
| agentName | No | Agent requesting context |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only says 'generate a summary' with no mention of side effects, permissions, or response format. This is insufficient for a tool that may read sensitive project state.
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 sentence with no unnecessary words. However, it could be slightly expanded to include context without becoming verbose.
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?
The tool has no output schema and a simple input, but the description does not clarify what the summary includes (e.g., recent changes, key issues). Given siblings like 'get_project_state' and 'generate_report', more detail is needed to avoid confusion.
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 single parameter 'agentName' is already described in the schema. The description adds no extra meaning. With 100% schema coverage, the baseline of 3 applies; no enhancement needed.
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 it generates a summary of project context, which is a specific verb and resource. However, it does not differentiate from sibling tools like 'generate_report' or 'get_project_state', leaving ambiguity about the summary's scope.
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 on when to use this tool versus alternatives. With many sibling tools for information retrieval, the description should indicate when a context summary is appropriate, e.g., for an overview vs detailed reporting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate_reportC
Generate a project status report
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Type of report to generate |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits. It does not state whether the tool is read-only, what side effects occur, or what the output looks like.
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, concise sentence. It is front-loaded but lacks necessary detail, which slightly reduces effectiveness.
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 simplicity of the tool (1 parameter, no output schema), the description is too minimal. It does not explain report contents, behavior of subtypes, or integration with other tools.
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 covers 100% of parameters with enums and descriptions, so the description adds no additional meaning beyond the schema. A baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (generate) and resource (project status report). However, it does not differentiate this tool from similar siblings like 'generate_context_summary', missing an opportunity to specify the unique purpose.
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. There is no mention of prerequisites, contexts, or when to avoid using it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_all_tasksB
Get all tasks in the system
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | Filter tasks by role |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden of behavioral disclosure. It only states 'get all tasks', implying a read operation, but it does not mention any side effects, authorization needs, or constraints like pagination or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence that directly states the tool's action. It wastes no words and is front-loaded, making it efficient for an agent to parse.
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?
The tool is simple with one optional parameter and no output schema. The description is sufficient for a basic list-all operation. However, it could be slightly more complete by mentioning ordering or scope, but it is not critically lacking.
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 provides 100% coverage of the one parameter ('role'), with a description. The tool description does not add additional meaning beyond what the schema already conveys. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get all tasks in the system' clearly states the verb (get) and resource (tasks), making the purpose obvious. However, it does not differentiate from sibling tools like 'get_task_status' or 'diagnose_tasks', which may cause confusion.
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. With many sibling tools (e.g., get_task_status, diagnose_tasks), the agent would benefit from context on when to retrieve all tasks vs. specific filters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_loop_statusC
Get the current status of the autonomous loop
| Name | Required | Description | Default |
|---|---|---|---|
| agentName | Yes | Name of the agent to check |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must bear the full burden. Only states 'get the current status' without disclosing side effects, permissions, or expected behavior. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with verb, no wasted words. Could be slightly more structured but is appropriately concise for a simple tool.
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 simplicity (1 param, no output schema, no annotations), the description is minimally adequate. However, it does not clarify what the 'status' contains (e.g., running/stopped, errors), leaving some gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter documented. The description adds no extra meaning beyond the schema, so baseline score of 3.
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?
Clear verb 'Get' and resource 'current status of the autonomous loop'. However, sibling tool 'status' also exists, and the description does not differentiate it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use versus alternatives like 'status' or the loop start/stop tools. The description only states what the tool does, not when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_project_planB
Get the current active project plan
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only says 'Get', implying a read operation, but lacks details on idempotency, side effects, or what constitutes a 'plan'. Could mislead an agent about the nature of the 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?
Extremely concise single sentence with no redundant information. Every word is necessary.
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?
The description is too sparse given the lack of output schema and annotations. It does not explain what a project plan includes, how to interpret the result, or how it relates to sibling tools like get_task_status.
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?
No parameters exist, and schema coverage is 100%. The description does not add any parameter-level detail, but baseline is 3 given high 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 it retrieves the current active project plan, with a specific verb and resource. It distinguishes from siblings like get_project_state and get_all_tasks.
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 on when to use this tool versus alternatives like get_project_state or get_all_tasks. No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_project_stateC
Get current project state
| Name | Required | Description | Default |
|---|---|---|---|
| component | No | Specific component to get (optional) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully convey behavior. It only says 'Get current project state' without explaining what state entails, whether it is read-only, or any other characteristics.
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 very short (one phrase), which is concise but not enough to be adequately informative for an AI agent.
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 output schema and no annotations, the description should include what the state contains or how it is represented, but it does not.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single optional parameter, so the baseline is 3. The description adds no extra meaning beyond the schema's parameter 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 'Get current project state' clearly states the verb and resource, but among many sibling getter tools (get_project_plan, get_task_status, etc.), it does not differentiate what 'state' specifically covers.
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_project_plan or get_task_status.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_task_statusB
Get status of a specific task
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | Yes | Task ID to get status for |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It only states 'Get status' without explaining what status values exist, whether the call is idempotent, or any side effects. For a read operation, minimal transparency is acceptable, but the lack of any detail beyond the schema is a 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 short and front-loaded, but it is overly minimal. It could include additional context without losing conciseness, such as expected response format or typical statuses.
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?
Without an output schema, the description should clarify what the tool returns. It does not mention the structure or possible values of status, leaving ambiguity. For a task status tool, more detail is expected.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single required parameter 'taskId', which already has a description. The tool description adds no new information about the parameter, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get status of a specific task' clearly identifies the action (get) and resource (status of a task). It effectively differentiates from siblings like 'get_all_tasks' and 'get_loop_status' by focusing on a single task's status.
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 on when to use this tool versus alternatives. Siblings like 'diagnose_tasks' or 'get_all_tasks' serve different purposes, but the description provides no context for choosing this tool. No exclusions or prerequisites mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
initC
Initialize agent with role-based autonomous workflow
| Name | Required | Description | Default |
|---|---|---|---|
| mission | No | Ad-hoc mission to execute (pauses main project plan) | |
| agentName | Yes | Name of the agent initializing | |
| autonomous | No | Start autonomous loop immediately (default: false) | |
| checkInterval | No | Seconds between checks for autonomous mode (default: 120) | |
| maxIterations | No | Max iterations for autonomous mode (default: 500) | |
| createProjectPlan | No | Create new project plan from requirements (default: false) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only says 'initialize' without explaining side effects, authentication needs, or what happens to the agent. No behavioral traits are disclosed.
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 sentence, which is concise, but it lacks substance. It is not verbose, but it could provide more information without being wordy.
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 has 6 parameters, nested objects, and no output schema, the description fails to explain return values, workflow effects, or how parameters like 'mission' interact. It is insufficient for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with all parameters described. The description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Initialize agent with role-based autonomous workflow' uses a specific verb and resource, but lacks clarity on what 'initialize' entails. It does not distinguish from siblings like 'start_autonomous_loop' or 'create_project_plan', which are related but not contrasted.
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. For example, it does not mention whether init is a prerequisite for other tools or when to use it over start_autonomous_loop.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_ticketsB
List tickets with optional filtering
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by type | |
| status | No | Filter by status | |
| priority | No | Filter by priority |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose behavior such as pagination, sorting, or rate limits. Minimal transparency beyond the basic operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no fluff, but could be slightly more informative. Efficient but lacks front-loading of key details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema or behavioral hints. For a list tool, missing details on result format, pagination, or ordering makes it incomplete for an AI agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for each parameter. The description adds no extra meaning beyond the schema; it only states 'optional filtering', so it meets baseline but does not enhance understanding.
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?
Description clearly states the action (list) and resource (tickets), and mentions optional filtering, distinguishing it from sibling tools like create_ticket or update_ticket.
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 on when to use this tool versus alternatives like get_all_tasks or search tools. Does not specify context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
pingA
Simple ping to test server connectivity
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits such as side effects, error handling, or timeouts. Since no annotations are provided, the description carries the burden of transparency, which it fails to meet.
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 a single phrase that fully captures the tool's purpose. Every word is necessary and there is no redundancy.
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 simplicity, the description is nearly complete. However, it does not explicitly mention the return format or success/failure indication, which would be expected for a connectivity test.
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?
There are no parameters, so the baseline is 4. The description adds no parameter information because none exists, and the schema coverage is 100% trivially.
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 tool's purpose: a simple ping to test server connectivity. It uses a specific verb ('ping') and identifies the resource ('server connectivity'), making it distinct from sibling tools like 'get_loop_status' or 'diagnose_tasks'.
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 or when not to use it. The description only implies basic connectivity testing, but lacks explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
reset_task_dependenciesA
Reset task dependencies for tasks that are blocked by completed/missing tasks
| Name | Required | Description | Default |
|---|---|---|---|
| taskIds | No | Task IDs to reset dependencies for (or empty for all blocked tasks) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It does not disclose whether the operation is destructive, whether it removes all dependencies or just those to completed/missing tasks, or what permissions are required. This lack of detail is a significant gap for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the purpose. No unnecessary words or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional parameter, no output schema, no annotations), the description is adequate but not complete. It lacks details on effects, reversibility, and error conditions, which would be helpful for appropriate 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 coverage is 100% as the parameter 'taskIds' already has a description in the schema. The description adds no new meaning beyond what the schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool resets task dependencies specifically for tasks blocked by completed or missing tasks. This distinguishes it from sibling tools like get_task_status or diagnose_tasks which read or analyze rather than modify.
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 implies usage when dependencies are blocked by completed/missing tasks, but does not provide explicit when-not-to-use guidance or mention alternative tools that might be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
review_workC
Submit a review of submitted work
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | Review decision | |
| taskId | Yes | Task ID being reviewed | |
| feedback | Yes | Review feedback | |
| actionItems | No | Action items for revision |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only says 'Submit a review,' implying a write operation, but does not disclose side effects (e.g., status update, notifications) or whether the review is reversible. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single concise sentence with no extraneous words. Could be slightly expanded for clarity (e.g., specifying 'approve or request revision'), but stays 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?
For a tool with 4 parameters, no output schema, and no annotations, the description is too brief. It omits the purpose of actionItems, the workflow context (e.g., after submit_work), and what happens after a review.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions (e.g., 'Review decision', 'Review feedback'). The description adds no extra meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Submit a review of submitted work,' which clearly identifies the action (reviewing) and the resource (submitted work). It distinguishes from sibling 'submit_work' but could be more specific about what reviewing entails (e.g., approval or revision).
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 on when to use this tool versus alternatives like 'submit_work', 'diagnose_tasks', or 'generate_report'. The description does not specify prerequisites (e.g., work must be submitted first) or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
send_batch_directivesB
Send multiple task directives at once. Use this to queue up multiple tasks for efficient workflow.
| Name | Required | Description | Default |
|---|---|---|---|
| tasks | Yes | Array of task directives to create |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only says 'Send multiple task directives at once' without disclosing important behavioral traits such as atomicity, error handling, performance implications, or whether the batch processing is synchronous or asynchronous.
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 only two sentences, front-loaded with the main action. It is concise, though it could be slightly improved by removing redundancy (e.g., 'at once' and 'multiple' indicate volume already).
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 (nested objects in the tasks array, no output schema, no annotations), the description is too brief. It omits critical context like limits on the number of tasks, whether the batch is all-or-nothing, or what the response contains.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (the 'tasks' parameter is fully described in the schema). The description adds minimal extra meaning beyond 'multiple task directives', so it meets the baseline but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Send' and resource 'multiple task directives', and the phrase 'queue up multiple tasks for efficient workflow' differentiates it from sibling tools like send_directive, which is presumably for single directives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It says 'Use this to queue up multiple tasks for efficient workflow', which implies when to use (batch case), but it does not explicitly exclude alternatives like send_directive for single tasks, nor does it mention when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
send_directiveB
Send a task directive to the development team. Can create single or batch tasks with dependencies.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Title of the task | |
| taskId | Yes | Unique identifier for the task | |
| priority | No | Task priority (default: medium) | |
| blockedBy | No | Task IDs currently blocking this task | |
| dependsOn | No | Task IDs this task depends on | |
| requirements | No | List of requirements | |
| specification | Yes | Detailed specification of what needs to be done | |
| acceptanceCriteria | No | Acceptance criteria for the task |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral disclosure burden. It mentions creating tasks with dependencies but does not address authentication requirements, rate limits, side effects, or what happens upon creation. For an 8-parameter tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no wasted words. However, it lacks structure or front-loading of key details; for example, it could separate the core action from the batch capability. Still, it is efficient for its length.
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 has 8 parameters, no output schema, and no annotations, the description is incomplete. It does not explain return values, error conditions, or how batch creation works. A more thorough description is needed for full context.
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, so the description adds limited value. It mentions 'single or batch tasks with dependencies,' providing minor context for 'blockedBy' and 'dependsOn', but does not explain parameter formats or usage beyond the schema.
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 tool's function: sending task directives to the development team with dependency handling. It distinguishes itself from siblings like 'send_batch_directives' by covering both single and batch tasks.
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 implies usage for creating directives with dependencies but does not explicitly guide when to use this tool versus other similar tools like 'send_batch_directives' or 'create_ticket'. No alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
start_autonomous_loopC
Start an autonomous work loop that continuously checks for and processes work
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Type of autonomous loop | |
| agentName | Yes | Name of the agent starting the loop | |
| checkInterval | No | Seconds between checks (default: 30) | |
| maxIterations | No | Maximum loop iterations (default: 100) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It mentions the loop runs continuously, but does not disclose blocking behavior, how to stop it (despite sibling 'stop_autonomous_loop'), potential side effects, error handling, or performance implications. This is a significant gap for a long-running process.
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 sentence that is front-loaded with the action. It is concise with no wasted words, though it could benefit from slightly more detail for clarity.
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?
The tool starts a potentially long-running loop but has no output schema; the description does not explain return values, how to monitor progress (despite sibling 'get_loop_status'), or termination behavior. Given the complexity and 4 parameters, the description is incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add any meaning beyond the schema; it does not elaborate on the enum values (mode) or default values for numeric parameters. The agent would rely solely on the schema descriptions.
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 'Start' and the resource 'autonomous work loop', and explains what the loop does: 'continuously checks for and processes work'. It distinguishes from siblings like 'stop_autonomous_loop' and 'get_loop_status' by focusing on starting the loop, though not explicitly naming alternatives.
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 (e.g., when to start a loop vs. other tasks like 'send_directive' or 'review_work'). There are no conditions, prerequisites, or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
statusC
Get current system status
| Name | Required | Description | Default |
|---|---|---|---|
| agentName | No | Agent requesting status |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It only restates the tool name without disclosing behavioral traits like read-only nature, auth requirements, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is appropriately brief for a simple tool, but could include additional context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool, the description is minimally adequate but lacks differentiation from similar sibling tools like get_loop_status. No return values are described, and output schema is absent.
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 single parameter 'agentName' is fully described in the input schema (100% coverage). The description adds no extra meaning beyond the schema, earning the baseline score of 3.
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 'Get current system status' clearly states a verb and resource, but it does not differentiate from sibling tools like get_loop_status or get_task_status, which target specific subsets of status.
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. The description lacks any contextual cues about when to invoke status vs. get_loop_status or get_task_status.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
stop_autonomous_loopC
Stop the autonomous work loop
| Name | Required | Description | Default |
|---|---|---|---|
| agentName | Yes | Name of the agent stopping the loop |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description gives no behavioral details such as whether the stop is immediate or graceful, if it is idempotent, or what side effects occur. Limited transparency 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but may be too brief for a tool that stops a process. Could be more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema provided, and the description does not explain the effect of stopping the loop (e.g., what happens to ongoing tasks, agent state). Lacks completeness for a control action.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description does not add significant meaning beyond the parameter name. The parameter 'agentName' is documented simply as 'name of the agent stopping the loop', which is adequate but not enhanced.
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 ('stop') and resource ('autonomous work loop'), but it does not differentiate from the similar sibling tool 'stop_autonomous_work'. The purpose is somewhat ambiguous as there are two stop-related 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?
No guidance on when to use this tool versus alternatives like 'stop_autonomous_work' or 'start_autonomous_loop'. Lacks context for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
stop_autonomous_workC
Stop autonomous work mode
| Name | Required | Description | Default |
|---|---|---|---|
| agentName | Yes | Name of the agent stopping work |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavior. It only says 'Stop autonomous work mode', omitting effects, reversibility, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: one sentence with no wasted words. Appropriate length for the simplicity.
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 too brief. It does not explain what stopping entails, making it incomplete for effective 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 covers 100% of parameters with a description for 'agentName'. The tool description adds no extra meaning beyond the schema, meeting the baseline but not exceeding it.
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 ('Stop') and the target ('autonomous work mode'). While clear, it does not differentiate from the sibling tool 'stop_autonomous_loop', which could cause confusion.
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 on when to use this tool versus alternatives like 'stop_autonomous_loop'. Lacks context about prerequisites or scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
submit_workC
Submit completed work for review
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | Files changed or created | |
| taskId | Yes | Task ID this submission is for | |
| summary | Yes | Summary of work completed | |
| testResults | No | Test results |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as idempotency, side effects, permission requirements, or workflow triggers (e.g., does submission automatically notify a reviewer?). The term 'submit' implies mutation, but no further 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, concise sentence with no unnecessary words. It could be slightly expanded to include behavioral context without losing conciseness.
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 absence of an output schema and the tool's role in a workflow, the description fails to explain what happens after submission (e.g., status changes, review initiation). It leaves the agent without critical workflow context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema parameter descriptions, which are already present.
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 'Submit completed work for review' clearly states the action (submit) and the resource (completed work), distinguishing it from sibling tools like review_work. However, it could be more specific about the submission 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?
No guidance is provided on when to use this tool versus alternatives such as review_work or create_ticket. There is no mention of prerequisites, conditions, or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update_plan_progressC
Update project plan progress when phase is complete
| Name | Required | Description | Default |
|---|---|---|---|
| adjustments | No | Any adjustments to the plan | |
| phaseComplete | No | Mark current phase as complete |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It mentions updating progress but does not disclose effects like whether the phase advances automatically, what triggers the update, or any side effects. The description is too vague to inform an AI agent about the tool's full behavior.
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 concise sentence with no wasted words. It is front-loaded with the action. However, it lacks structure (e.g., bullet points for parameters) which could improve readability.
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 output schema and a moderate complexity (2 parameters, one nested object), the description is incomplete. It does not describe return values, error conditions, or prerequisites like whether the user must have certain permissions or the plan must already exist. The nested 'adjustments' object is not elaborated.
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 baseline is 3. The description adds no new meaning beyond the schema: 'phaseComplete' is already described in schema as 'Mark current phase as complete'. The nested 'adjustments' parameter has minimal schema description, but the tool description does not clarify it further.
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 specifies the action ('Update'), resource ('project plan progress'), and condition ('when phase is complete'), making the purpose clear. It distinguishes from sibling tools like update_project_state and update_ticket by focusing on plan progress, though it could be more explicit about marking phases.
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 given on when to use this tool versus alternatives. The phrase 'when phase is complete' implies a usage context, but there is no comparison to update_project_state or other siblings, nor any mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update_project_stateC
Update the state of a project component
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | New state data | |
| component | Yes | Component name to update |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only says 'update', which implies mutation but lacks details on side effects, permissions, or error conditions. For a write operation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the purpose. It is front-loaded and without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With two parameters, no output schema, and no annotations, the description is too short. It does not explain what a 'component' is, what valid states are, or what the response looks like, leaving the agent underinformed.
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 descriptions cover 100% of parameters, so the description adds no extra value beyond the schema. Baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it updates a project component's state, using specific verb and resource. However, it does not differentiate from sibling tools like 'update_ticket' or 'update_plan_progress', which could also update states.
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 on when to use this tool versus alternatives. For example, it doesn't specify whether this is for internal state updates or for external status changes, leaving the agent uncertain.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update_ticketC
Update an existing ticket
| Name | Required | Description | Default |
|---|---|---|---|
| updates | Yes | Updates to apply | |
| ticketId | Yes | ID of ticket to update | |
| agentName | Yes | Agent making the update |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of behavioral disclosure. It does not mention side effects, permissions required, or whether updates are irreversible. For a mutation tool, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no fluff, but it is almost too concise. It lacks any structure or additional context that could help an agent, though it communicates the core purpose without waste.
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?
The description fails to explain the return value or behavior of the tool. Since there is no output schema, the description should indicate what happens after the update (e.g., returns the updated ticket). It also does not detail the nested 'updates' object structure.
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 provides descriptions for all three parameters, achieving 100% coverage. The description adds no additional meaning beyond what the schema already states, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the resource ('existing ticket'). It distinguishes from sibling tools like 'create_ticket' and 'list_tickets'. However, it is slightly generic and could be more specific about what fields can be updated.
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 on when to use this tool versus alternatives. There is no mention of prerequisites, such as needing an existing ticket ID or context about when updates are appropriate. The description lacks any situational advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
28 tool updates
v1.0.0- First observed
answer_question - First observed
ask_question - First observed
create_mission - First observed
create_project_plan - First observed
create_ticket - First observed
diagnose_tasks - First observed
generate_context_summary - First observed
generate_report - First observed
get_all_tasks - First observed
get_loop_status - First observed
get_project_plan - First observed
get_project_state - First observed
get_task_status - First observed
init - First observed
list_tickets - First observed
ping - First observed
reset_task_dependencies - First observed
review_work - First observed
send_batch_directives - First observed
send_directive - First observed
start_autonomous_loop - First observed
status - First observed
stop_autonomous_loop - First observed
stop_autonomous_work - First observed
submit_work - First observed
update_plan_progress - First observed
update_project_state - First observed
update_ticket
TDQS
Scored across 28 tools
Most tools have distinct purposes but there is some overlap between create_mission, create_project_plan, and send_directive for task creation. Also, ask_question/answer_question are clear pairs. Overall, an agent can distinguish, but minor ambiguity exists.
Tool names follow a mostly consistent verb_noun pattern in snake_case (e.g., create_mission, get_project_state). However, a few tools like 'ping', 'status', and 'init' lack a noun after the verb, deviating from the pattern.
28 tools is slightly high but reasonable for a collaboration server covering missions, projects, tasks, tickets, autonomous loops, and reporting. The scope justifies the count, though some consolidation could help.
The tools cover core lifecycle operations for projects and tickets but are missing delete operations for missions, tasks, and tickets. Also, no explicit update_task tool exists. This leaves some gaps that agents may need to work around.
Maintenance
Related MCP Connectors
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
- DartOAuthcom.dartai
AI-native project management for tasks, docs, collaboration, and agents.
- ParleyOAuthdev.weldra
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Project registry, behavioral specs, and engineering threads for AI coding agent workflows.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables collaboration between multiple AI models (GPT, Claude, Gemini) to work together on complex tasks, with intelligent task distribution and role-based expert assignment for code development, review, and optimization.187 npm49MIT
- AlicenseBqualityDmaintenanceEnables Claude to collaborate with Gemini for code reviews, second opinions, and iterative software development. It facilitates multi-step workflows including PRD creation and code generation through an AI orchestration framework.211 npm1MIT
- FlicenseNot gradedqualityDmaintenanceCoordinates multiple Claude Code agents to work collaboratively on projects with role-based task management, shared state, and automated code review.5 npm2-
- AlicenseDqualityBmaintenanceEnables Claude Code as a team leader to delegate tasks to GPT and Gemini experts, supporting multi-LLM collaboration with tools for consultation, code review, design, and background execution.769 npmMIT