Skip to main content
Glama
Sign In

ContextLayer

by io.github.DotNova
OverviewDiscussionsAdmin

start_session

Start a work session. If a project is provided (project_name or project_id), the session is bound to it; if neither is provided, an unbound (projectless) session is created — useful when the work isn't tied to a specific project. Reuses an existing active session for the same scope (per-project, or one global projectless session per user). Task type: coding, review, planning, debugging, research, meeting, other.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_type": "<task_type>"
    },
    "name": "start_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceNoSource client identifier (e.g. 'claude-code', 'claude-web', 'chatgpt', 'cursor'). Helps track which tool created the session.
task_typeYesType of task: coding, review, planning, debugging, research, meeting, other
project_idNoProject ID to start the session in (optional if project_name provided)
project_nameNoProject name (optional, alternative to project_id)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden of disclosing behavior. It explains key side effects: binding to a project, creating an unbound session, and reusing an existing active session. It stops short of discussing permissions or failure modes, but covers core behavior well.

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

Conciseness5/5

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

The description is tightly packed into four purposeful sentences: core action, conditional project semantics, reuse behavior, and task type enumeration. No fluff, well-front-loaded.

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

Completeness4/5

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

The description is complete enough for an agent to select and invoke the tool correctly, covering parameters, behavior, and usage context. Minor gaps exist around return value and error conditions, but the tool's purpose is clearly conveyed.

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 description adds meaning beyond the schema by clarifying that project_name and project_id are alternative ways to bind a session, and explicitly addresses the case when neither is provided. It also enumerates the allowed task_type values, supplementing the schema.

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

Purpose5/5

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

The description clearly states the verb 'Start' and resource 'work session', and differentiates between project-bound and projectless sessions. It also mentions reuse of active sessions, distinguishing it from sibling tools like end_session.

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

Usage Guidelines4/5

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

The description provides clear context on when to use a project-bound session vs a projectless one, and notes the reuse behavior. It does not explicitly name alternative tools, but the conditions are stated sufficiently.

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

All ContextLayer toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources