mailbox

create_test_outbound_mail

Create a sandbox outbound mail record without uploading a real document. The record is always test_mode=true, cost_cents=0, includes estimated_live_cost_cents and cost_breakdown, and queues a mail.submitted webhook. USPS First-Class Mail has a published $2.00 one-page baseline. Extra pages add configured printing plus any postage increase from weight. If an account's normal first-page formula is lower, cost_breakdown.first_class_baseline_adjustment_cents itemizes the difference separately from carrier postage. Color pages cost $0.70/page total by default before handling and postage: $0.40/page base B&W printing plus a $0.30/page additive color upgrade. In cost_breakdown, color_printing_per_page_cents is the total color-page printing price (70 cents by default), while color_surcharge_per_page_cents is the additive upgrade only (30 cents by default). Account-specific pricing can override these defaults; cost_breakdown is authoritative. FedEx and UPS estimates use the same configured origin and destination zone/region logic as production; FedEx Overnight adds a fixed $18.00 after the otherwise-calculated carrier baseline and reports service_adjustment_cents: 1800. Use with a sandbox key to rehearse outbound workflows before sending real physical mail.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`color`	No	Color pages cost $0.70/page total by default before handling and postage: $0.40/page base B&W printing plus a $0.30/page additive color upgrade. In cost_breakdown, color_printing_per_page_cents is the total color-page printing price (70 cents by default), while color_surcharge_per_page_cents is the additive upgrade only (30 cents by default). Account-specific pricing can override these defaults; cost_breakdown is authoritative.
`metadata`	No	Arbitrary metadata echoed in responses and webhooks.
`mail_class`	No	Mail class to simulate. Postal or carrier service. Do not infer speed, tracking, or proof from carrier marketing names. Use first_class for ordinary lowest-cost USPS letters with no carrier tracking number by default. USPS First-Class Mail has a published $2.00 one-page baseline. Extra pages add configured printing plus any postage increase from weight. If an account's normal first-page formula is lower, cost_breakdown.first_class_baseline_adjustment_cents itemizes the difference separately from carrier postage. Use priority for faster USPS Priority Mail with USPS Tracking, but not Certified Mail proof; priority has a $15.00 published one-page floor. Use certified for USPS tracking plus proof of mailing/delivery; certified has a $20.00 published one-page floor. Use certified_return_receipt when electronic return-receipt evidence is required; certified_return_receipt has a $24.00 published one-page floor. Use fedex_ground or ups_ground for budget private-carrier tracking; fedex_express means FedEx Express Saver/third-business-day, fedex_2day and ups_2day mean second-business-day, and fedex_overnight or ups_next_day mean next-business-day. FedEx express classes use the Standard List document baseline from the configured fulfillment origin unless FedEx One Rate is explicitly configured operationally; fedex_overnight then adds a fixed $18.00 customer price adjustment (service_adjustment_cents: 1800). The same printing rates apply to every mail_class. Color pages cost $0.70/page total by default before handling and postage: $0.40/page base B&W printing plus a $0.30/page additive color upgrade. In cost_breakdown, color_printing_per_page_cents is the total color-page printing price (70 cents by default), while color_surcharge_per_page_cents is the additive upgrade only (30 cents by default). Account-specific pricing can override these defaults; cost_breakdown is authoritative.	first_class
`page_count`	No	Simulated page count used for pricing.
`agent_notes`	No	Optional facility/operator notes for the simulated mailpiece.
`recipient_zip`	No	Recipient ZIP code. Affects estimated live postage, private-carrier zone, and FedEx local/regional/national area.	94105
`recipient_city`	No	Recipient city.	San Francisco
`recipient_name`	No	Recipient name for the simulated mailpiece. Optional when recipient_company is provided.	Test Recipient
`recipient_line1`	No	Recipient street line 1.	123 Test Street
`recipient_state`	No	Recipient 2-letter state code.	CA
`recipient_company`	No	Company or organization line for the simulated mailpiece. Optional when recipient_name is provided.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes	Created sandbox outbound mail job and webhook status.

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only declare mutating/non-idempotent/non-destructive. The description adds substantial behavioral detail: test_mode=true, cost_cents=0, cost_breakdown/estimated_live_cost_cents, webhook queuing, pricing formula overrides, and carrier-specific service adjustments. No contradiction with annotations.

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 long but well structured: core behavior first, then pricing defaults, carrier notes, and usage. Each sentence carries meaning, and the detail is warranted because cost_breakdown is a major output. It is not as tight as it could be because some pricing text is duplicated in the schema.

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?

Given the output schema exists and covers return values, the description covers all necessary context: what the record is, side effects, sandbox usage, pricing behavior, and authoritative cost fields. Nothing critical is missing for an agent to call it correctly.

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 baseline 3 is appropriate. The description and input schema repeat most pricing and mail_class guidance; the description adds overall behavioral context but no new parameter-level semantics 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?

The description opens with a specific verb and resource: 'Create a sandbox outbound mail record without uploading a real document.' The sandbox/test framing and the closing 'before sending real physical mail' clearly distinguish this from the real send_outbound_mail sibling.

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?

It gives explicit context: use with a sandbox key to rehearse outbound workflows before real mail. It does not explicitly name the alternative tool or state 'do not use in production,' but the sandbox-key requirement and the contrast with real physical mail provide a clear implied exclusion.

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

All mailbox 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

A4.1/5.0

Disambiguation4/5

Most tools map cleanly to distinct resources and actions, forming clear list/get pairs for outbound mail, inbound mail, and postal threads. The main ambiguity is between get_facility_messages and list_facility_conversations, which both target the same Austin HQ conversation, and get_mailbox versus list_inbound_forwarding_addresses are closely related address lookups.

Naming Consistency5/5

All tool names use a consistent lowercase snake_case verb_noun pattern with familiar verbs like get, list, send, cancel, create, update, and propose. There are no mixed naming conventions or vague generic names.

Tool Count3/5

19 tools is within the 16-25 range that feels heavy for a single-domain MCP server. The broad outbound/inbound lifecycle, threads, facility messaging, MAILBOX.md, usage, and webhook support justify much of the count, but a few tools such as the facility conversation list/get pair could reasonably be consolidated.

Completeness4/5

The tool surface covers the core physical mail workflow well: test and real outbound sends, cancellation, inbound forwarding and retrieval, postal threads, facility communication, MAILBOX.md sync, usage, and webhooks. Minor gaps exist around webhook inspection/removal and direct document download, but these are unlikely to cause agent dead-ends in the main workflows.

Resources

Need Help?