brain-v42

Overview Schema Source Related Servers Discussions Admin

brain_session_start

Idempotent

Start or replay a concurrent coding-agent session from an explicit command, using project and client keys to track retries and parallel sessions in persistent memory.

Instructions

Start or replay a concurrent session from an explicit user command.

briefing defaults to full detail; compact returns counts and IDs in at most 4,000 characters. Focus text appears only in session.started_focus.

An agent tracer is the only session the server opens or closes on its own; no hook and no auto-close may invoke this lifecycle boundary.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`briefing`	No		full
`client_key`	Yes	Stable identity for one intended session. Reuse it for every retry of that session; use a distinct stable key for each parallel session.
`project_key`	Yes

Output Schema

TableJSON Schema

Name	Required	Description
`session`	Yes	Persistent state of one explicitly controlled concurrent session.
`briefing`	No
`replayed`	Yes
`open_session_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.7.3Oct 17, 2026

addedInput schema / properties / briefing

Added value: +{
+  "default": "full",
+  "enum": [
+    "full",
+    "compact"
+  ],
+  "type": "string"
+}

First observedv0.6.1Sep 23, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare write/idempotent/non-destructive, so the description correctly focuses on non-obvious behavior: replay semantics, the briefing size cap, and the fact that no hook or auto-close can drive this lifecycle boundary. That is meaningful context beyond the structured fields, though permission/auth requirements are not covered.

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

Conciseness4/5

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

Front-loads the core action in the first sentence and each subsequent sentence carries distinct content (briefing behavior, lifecycle constraints). The third sentence is somewhat dense but not wasteful.

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?

With an output schema present, return values need not be explained, and the description covers the mutation's key semantics and the lifecycle restriction. The only notable gap is the undocumented `project_key` parameter.

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

Parameters3/5

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

Schema coverage is only 33%, so the description must compensate. It does explain the `briefing` semantics well ('full' detail vs. compact counts/IDs capped at 4,000 chars, focus only in session.started_focus), but `project_key` remains undocumented in both schema and description.

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

Purpose4/5

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

States a specific verb and resource ('Start or replay a concurrent session') and adds a scope qualifier ('from an explicit user command'). It is fairly distinguishable from siblings, though the boundary against brain_session_resume (vs. 'replay') is not made explicit.

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?

Gives a positive trigger ('from an explicit user command') and a clear exclusion ('no hook and no auto-close may invoke this lifecycle boundary'), which is real when/when-not guidance. It stops short of naming which sibling to use for the non-explicit cases.

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

Deploy Server