Conduit Agentic Commerce

Notify org members

agent_notify

Idempotent

Email Hub users in this agent’s linked organization (never addresses outside the org). to=all or { user_id } / { role } / { email } matching agent_organization members. Optional actions (Hub URLs only), severity, idempotency_key. Channel is email.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	Who to notify: "all", { user_id }, { user_ids }, { role }, { roles }, or { email } matching an org member. Never an address outside the org.
`body`	Yes	Plain-text body, max 4000 characters. Conduit wraps HTML; do not send markup.
`title`	Yes	Subject line, max 120 characters
`actions`	No	Optional buttons, max 3. Hosts outside Conduit are rejected.
`channel`	No	Delivery channel. Email only — omit or pass email
`dry_run`	No	If true, resolve recipients and from-address without sending or storing
`agent_id`	Yes	Linked agent sending the message
`order_id`	No	Optional order correlation
`severity`	No	info (default), warning, or urgent — affects subject prefix and accent
`search_id`	No	Optional search correlation
`session_token`	No	Session token from agent_authenticate — required whenever agent_id is passed
`idempotency_key`	No	Replay key — same agent + key returns the original notify_id without sending again

Output Schema

TableJSON Schema

Name	Required	Description	Default
`from`	No
`hint`	No
`next`	No
`error`	No
`detail`	No
`failed`	No
`channel`	No
`dry_run`	No
`delivered`	No
`notify_id`	No
`recipients`	No
`idempotent_replay`	No

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already provide readOnly=false, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral guardrails beyond those flags: recipients must be org members, action URLs must be Conduit hosts, and delivery is email-only. This helps an agent avoid dangerous or unauthorized sends.

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

Conciseness5/5

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

Three tightly packed sentences with no filler. The primary purpose and org-only restriction are front-loaded, followed by recipient forms and constraints. Every sentence earns its place.

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

Completeness5/5

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

The description is complete at a glance for tool selection and basic invocation, and the input schema covers all field-level details including auth requirements, length limits, enums, and host restrictions. Since an output schema exists, return-value explanation is unnecessary.

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 the baseline is 3. The description summarizes recipient forms and lists optional capabilities like actions, severity, and idempotency_key, but these mostly restate what the input schema already documents rather than adding deeper parameter semantics.

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?

The description opens with a specific verb and resource: 'Email Hub users in this agent’s linked organization.' It clearly scopes the tool to notifying org members and immediately adds the hard restriction 'never addresses outside the org,' which distinguishes it from broader outreach tools like agent_outreach even without naming them.

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?

The description gives clear selection context: use this tool to email members of the linked org, with explicit recipient shapes and constraints like 'Hub URLs only' and 'Channel is email.' It does not name alternative sibling tools or explicitly state when not to use it, so it stops just short of full 5.

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

All Conduit Agentic Commerce tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools map to a distinct resource/action, and the descriptions explicitly call out boundaries (e.g., agent_notify targets Hub users while agent_outreach targets external addresses). A few closely related pairs such as supply_delivery/supply_details and order_events/order_track could still cause misselection despite the clarifying notes.

Naming Consistency4/5

Tool names follow a clear lowercase snake_case resource-prefix pattern across agent_, order_, payment_, and supply_. The pattern is not perfectly uniform because some names are noun-only (agent_organization, payment_methods, supply_details) and order_update_status is a longer compound.

Tool Count4/5

At 19 tools, the set is slightly above the ideal range, but the count is justified by four distinct subdomains: agent identity/communication, orders, payments, and supply. No obvious filler tools are present.

Completeness4/5

The surface covers the main commerce workflow well: agent setup/auth, search and delivery probes, order execution/tracking/feedback/disputes, and payment mandates/methods. Minor gaps like no agent deletion, no payment-method disable, and no standalone order-detail tool are workable or arguably out of scope.

Resources

Need Help?