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

io.github.shafty023/agent-maildir

mailbox_publish

Send a message to a direct recipient, topic, or both from a bound agent; include reply_to to answer received messages.

Instructions

Send a message to a direct recipient, a topic, or both, from a bound agent. Use reply_to when answering a received message.

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": {
      "subject": "<subject>"
    },
    "name": "mailbox_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoDirect recipient agent ids
bodyNoJSON content, e.g. {summary, requestedAction, evidence}
typeNo
topicNo
subjectYes
reply_toNo
authorityNo
broadcastNoSend to every registered agent except the sender
from_agentNo
allow_no_subscribersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden of behavioral disclosure for an outbound, side-effecting operation. It hints at the binding prerequisite with 'from a bound agent' but says nothing about the consequences of `broadcast` (sending to every registered agent), what `allow_no_subscribers` changes, whether sends are idempotent or retractable, or what authority is required.

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?

Two short sentences, front-loaded with what the tool does and followed by the one routing rule. There is no filler, though the extreme brevity leaves behavior under-specified rather than over-written.

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

Completeness2/5

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

Given a 10-parameter mutation tool with no annotations, no output schema, and a nested `body` object, this description is too thin. An agent can infer the high-level action but not the risks of `broadcast`, the meaning of the delivery-control flags, or what a successful publish returns.

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?

With 10 parameters and only 30% schema description coverage, the description needs to compensate and largely does not. The single semantic contribution is the usage note for `reply_to`; the remaining underspecified parameters — `type` enum values, `authority`, `allow_no_subscribers`, `from_agent`, `topic` — get no explanation in either the schema or the 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?

The description uses a specific verb ('Send') with a clearly enumerated set of targets ('a direct recipient, a topic, or both') and names the source ('from a bound agent'), so an agent knows exactly what operation this is. It stops short of contrasting itself with the read-side siblings (mailbox_inbox, mailbox_read), but the send-vs-read distinction is apparent from the verb.

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

Usage Guidelines3/5

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

It gives one concrete routing instruction — 'Use reply_to when answering a received message' — which is genuinely useful for choosing between the `to` and `reply_to` paths. However, there is no guidance on when to choose `topic` versus `to` versus `broadcast`, no note on the prerequisite of being bound (implied only by 'from a bound agent'), and no exclusions relative to the inbox/read siblings.

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