Skip to main content
Glama

start_context

Initialize a work context for a coding task to track objectives, coordinate file locks, and log session history, preventing conflicts between agents.

Instructions

MANDATORY STEP 3: Start a new work context before beginning any coding task.

CRITICAL: You MUST call this tool AFTER create_project() and register_agent(). This establishes your current objective and enables:

  • Context tracking for the current task

  • File locking coordination

  • Session logging and history

  • Conflict prevention with other agents

This tool provides flexible project lookup. You can specify any combination of identifiers, and it will resolve to the matching project.

Priority: project_id > workspace_path > project_name

WHEN TO USE:

  • At the beginning of every coding session or task

  • When switching to a new objective or feature

  • When the user's request changes significantly

  • After completing one task and starting another

  • When you need to establish clear boundaries for your current work

WORKFLOW:

  1. create_project() - Create project (if new)

  2. register_agent() - Register yourself

  3. start_context() - Start work context (THIS STEP)

  4. lock_files() - Lock files you plan to modify (recommended)

  5. Begin coding

PRIORITY LEVELS:

  • "critical": Production outage, security vulnerability, critical bug fix

  • "high": Important features, significant refactoring, blocking issues

  • "medium": Standard development work (default)

  • "low": Documentation, minor optimizations, nice-to-have features

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idNoTask ID to link this context to (optional) - If provided, task will be auto-started
agent_idYesYour agent_id from register_agent() (required)
priorityNoPriority level - "critical", "high", "medium", or "low" (default: "medium")medium
objectiveNoClear, concise statement of what you're working on (required) - e.g., "Implement user authentication", "Fix API pagination bug"
project_idNoProject ID from create_project() (optional if project_name or workspace_path provided)
current_fileNoFile you're starting with (optional) - e.g., "src/auth/login.ts"
project_nameNoProject name to look up (alternative to project_id)
workspace_pathNoWorkspace directory path (alternative to project_id)
task_descriptionNoDetailed description of the work (optional) - Include specific requirements, acceptance criteria
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full transparency burden. It explains that the tool enables context tracking, file locking coordination, session logging, and conflict prevention, and it defines the priority value meanings. It does not discuss error conditions or return values, but the core behavior is well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is organized into labeled sections with a clear front-loaded purpose statement. Each section (WHEN TO USE, WORKFLOW, PRIORITY LEVELS) contributes unique information without redundancy, making it appropriately sized and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's role in the workflow, prerequisites, usage scenarios, and parameter semantics. It also provides a recommended sequence of operations (steps 1-5). Given the absence of an output schema, the description is sufficiently complete for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema documents all 9 parameters with 100% coverage. The description adds value by specifying the project lookup priority order (project_id > workspace_path > project_name) and by elaborating on the semantic meaning of each priority level. This goes beyond the schema's basic field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence 'Start a new work context before beginning any coding task' uses a specific verb and resource, and the 'MANDATORY STEP 3' framing distinguishes it from lifecycle siblings like switch_context and end_context. It clearly states what the tool does and why it is necessary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'WHEN TO USE' section enumerates explicit scenarios (every coding session, switching objectives, after task completion), and the workflow defines prerequisites (after create_project and register_agent). However, it does not explicitly contrast with switch_context or state when not to use it, so it falls short of a perfect 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/siddiquesahabaj/CoordMCP'

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