Skip to main content
Glama
io.github.shafty023/agent-maildir

io.github.shafty023/agent-maildir

mailbox_join

Register a client as a role in a local mailbox, subscribe its agent ID to role and project topics, and bind the MCP session so separate CLI agents can exchange durable messages.

Instructions

Join the mailbox as the holder of a role: register this client's agent id (- by default), subscribe it to role. and any project topics, and bind the MCP session. Claude Code can also confirm live push; other clients use the mailbox tools to poll.

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": {
      "role": "<role>"
    },
    "name": "mailbox_join"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleYesRole this session holds, e.g. reviewer
agentNoAgent id override; defaults to claude-<role>
projectNoProject names to subscribe to as project.<name>

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses agent-id registration, topic subscriptions, session binding, and the Claude Code live-push vs. other-client polling distinction. It omits idempotency, permission requirements, duplicate-join behavior, and error cases, which keeps it from a 5.

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?

The description is front-loaded with the core action and then lists effects in a compact, information-dense sentence. It is longer than a minimal description but every clause adds actionable detail about registration, subscription, or client behavior.

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?

For a composite, state-changing join tool with no annotations and no output schema, the description covers the main effects and client push/poll behavior. It still leaves important operational questions unanswered, such as what happens on re-join, whether the operation is idempotent, and how it relates to mailbox_bind.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds useful meaning beyond the schema: role determines the role.<role> subscription as well as the agent id, project names become project.<name> topics, and the agent override is contextualized. There is a minor tension between the description's <harness>-<role> default and the schema's claude-<role> default, but it does not undermine the semantics.

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?

The description states a specific action: joining the mailbox as a role holder, with concrete side effects (registering an agent id, subscribing to role/project topics, binding the session). It is distinguishable from siblings like mailbox_read or mailbox_publish, though it does not explicitly clarify its relationship to mailbox_bind.

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

Usage Guidelines2/5

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

The description implies this is an initial join/setup operation but gives no explicit when-to-use guidance, no exclusions, and no comparison to mailbox_bind or other siblings. The only alternative mentioned is polling via mailbox tools for non-Claude clients, which is behavioral rather than selection guidance.

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