Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

session_start

Single-call session briefing for the START of a session: last summary, recent lessons, health. It does not replace smart_recall for a concrete task. Returns: last session summary, recent lessons sorted by recency, relevant lessons for your focus area, brain health stats (counts of open failures and stale lessons), team telepathy (what teammates learned this week), predictive pre-warnings (if your focus area has known failure patterns), and memory crystals (compressed wisdom from old sessions). Also saves a session start marker so session_end can compute duration.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "session_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
focusNoKeywords for what you plan to work on today (e.g. "deploy infra api"). Used to surface relevant lessons at the top.
authorNoYour name or handle (e.g. "alice"). Enables Team Telepathy — filters YOUR lessons vs TEAM lessons from past 7 days.
providerNoCurrent AI provider (e.g. "claude-code", "copilot", "cursor", "windsurf"). Shown in the briefing header and saved so the next provider can see who was last active.
instance_idNoUUID of the cache instance.
workspace_pathNoAbsolute path to the project root. If no session_end was found (e.g. context limit hit), reads git log to reconstruct what happened since last session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden and does well: it discloses the write side effect (saves a session start marker so session_end can compute duration) and the git-log reconstruction fallback when no session_end exists. It stops short of saying whether repeat calls are safe or whether the marker is overwritten.

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-loaded with purpose and the sibling differentiation, and the return enumeration is justified since there is no output schema. The "Returns:" sentence is a long comma-chained run-on that could be tightened, but nothing is truly redundant.

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?

Given no output schema, the description appropriately explains the return payload and the persistence side effect. Idempotency and multi-call behavior are the remaining gap for a no-required-parameter tool that mutates state on invocation.

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 description coverage is 100%, so all five parameters are already documented with examples. The description reinforces meaning indirectly by tying "focus area" to surfaced lessons and teammates to telepathy, but adds no format, default, or interaction detail beyond 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?

States a specific verb and resource ("session briefing for the START of a session") and enumerates exactly what it returns (last summary, recent lessons, health stats, telepathy, pre-warnings, crystals). It also explicitly positions itself against smart_recall, so an agent can separate the two without opening schemas.

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?

Clear timing guidance ("START of a session") plus an explicit exclusion ("does not replace smart_recall for a concrete task"). What's missing is whether it should be called once per session or repeatedly, which matters for a tool that writes a start marker.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.