Skip to main content
Glama

handoff_brief

Generate a concise handoff summary of recent repository sessions across agents, covering goals, open todos, files touched, commands, errors, dead ends, checkpoints, and git status before resuming work.

Instructions

Summarize where the latest session(s) in a repository stopped, across agents.

Includes the goal, open todos, files touched, recent commands with outcomes, unresolved errors, dead ends (commands that failed repeatedly), the latest checkpoint note, and live git status. Call this when starting work in a repo that another agent (or an earlier session) worked on.

project: repository path (defaults to the server's working directory). exclude_source: skip one agent, e.g. "claude" to see only what others did.

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": "handoff_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNo
sourcesNoall
sessionsNo
exclude_sourceNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the exact contents of the brief, including derived intelligence like 'dead ends (commands that failed repeatedly)' and 'live git status', which implies the server inspects the working tree. It does not state read-only guarantees, cost, or latency, and the phrase 'across agents' leaves the multi-agent aggregation scope somewhat implicit.

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 the core action, then the content inventory, then the usage trigger, then parameter notes — a sensible ordering with no filler sentences. The middle content list is long but each item is a distinct deliverable, so it earns its space.

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

Completeness3/5

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

An output schema exists, so explaining return values is optional, and the description's inventory is a helpful complement rather than a substitute. However, two of four parameters go undocumented and the description never clarifies multi-agent aggregation semantics or whether the brief reads or writes anything, leaving real gaps for a tool that touches a working tree.

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

Parameters2/5

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

Schema description coverage is 0% across four parameters, so the description must compensate and only partially does: it explains 'project' (defaults to server working directory) and 'exclude_source' (with a concrete example). The 'sources' parameter (array-or-string, default 'all') and 'sessions' (integer, default 2) are never mentioned, so an agent cannot know how to broaden or narrow the aggregation from the description alone.

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?

Uses a specific verb and resource ('summarize where the latest session(s) in a repository stopped') and enumerates the payload: goal, open todos, files touched, commands with outcomes, errors, dead ends, checkpoint note, git status. It doesn't name a sibling tool it differs from, so an agent must infer how this differs from get_session or session_recall.

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 an explicit trigger: 'Call this when starting work in a repo that another agent (or an earlier session) worked on.' That is a clear usage context, but there is no statement of when not to use it or which sibling to prefer for a single-session deep dive or a cross-session comparison.

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