Skip to main content
Glama

Certified Mail Sender

Get a letter's status

get_letter
Read-only

Read a letter's state, timeline, tracking, proof_of_mailing, acceptance_expected_by, cancel_until, send_now, refund and next step. proof_of_mailing gives the USPS acceptance record; cite its local date as the mailing date. acceptance_expected_by gives the Eastern deadline while waiting, and is null after an individual-piece scan even if acceptance is missing. Relay next_step for the plain explanation. refund gives state, amount_cents and destination (card or balance). accepted means the processor accepted it or the balance was credited, not that the bank has posted it; manual means we will refund it by hand. Address checks usually finish in seconds. A pending address_status is retried each minute for up to a day; read again after a minute. A busy queue or partner delay can slow the check. Reading is free and changes nothing. first_usps_scan identifies the earliest individual-letter scan, not shipment receipt; only proof_of_mailing establishes acceptance. partner_checked_at is the last successful tracking poll, not the scan date. files_deleted_at means downloads are gone. Repeated adjacent checks carry observations and last_at; at stays the first check. Timestamps are UTC RFC 3339 with milliseconds; date-only fields retain their documented calendar dates. If the person mentioned a deadline, compare it with the delivery estimate and tell them plainly when the estimate falls after it. Use id with its API key, or the complete private letter_url from create_letter. Example: {"letter_url":"https://certifiedmailsender.com/l/?t="}

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": "get_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoLetter id; send the API key that created it in Authorization.
letter_urlNoComplete private letter_url or approval_url, including its t token.

Output Schema

NameRequiredDescriptionDefault
idYes
toYes
fromYes
modeYes
pagesYes
quoteYes
stateYesPersisted lifecycle state, not proof of mailing. printed comes from a Printed tracking observation; USPS acceptance requires proof_of_mailing. Reads can skip intermediate states. Test letters stop at submitted and never print or mail.
originYes
refundYesRefund record for a canceled, rejected or failed letter; null when no refund is due. Use state and amount_cents to tell the person what happened to their payment. Card refunds usually show within 5 to 10 business days; the bank decides exactly when.
serviceYes
send_nowYesWhether someone chose to skip the 30-minute cancellation hold. This never skips required payment or screening; auto-send keys have no per-letter approval step.
timelineYes
next_stepYes
created_atYesUTC RFC 3339 timestamp with milliseconds, YYYY-MM-DDTHH:mm:ss.sssZ.
letter_urlYesKeep this complete private link, including its t token. An anonymous letter can be read and canceled only with that token; an id alone or an API key created later cannot open it. A letter created with an API key can also be read and canceled with that same key.
preview_urlYes
receipt_urlNoPrivate token link to the USPS electronic Return Receipt PDF. Present only for certified_err in receipt_ready while files are retained; omitted means no downloadable receipt is available here, not that delivery failed. Keep the t token; this receipt is private like the letter PDF.
review_noteYes
address_noteYesThe address partner’s raw note, not wording to relay to the person. Use next_step for the plain-language version to tell the person.
approval_urlNoPrivate review page with the expected mailing date and USPS delivery estimate (not guaranteed). If the person mentioned a deadline, compare it with the delivery estimate and tell them plainly when the estimate falls after it.
cancel_untilYesThe scheduled end of the 30-minute cancellation hold, as an ISO 8601 / UTC RFC 3339 timestamp with milliseconds (YYYY-MM-DDTHH:mm:ss.sssZ); null for drafts or letters no longer cancellable. If skipped, this is when sending became eligible after payment. Cancellation remains possible until actual submission, even after this timestamp or during review; no extra cancellation period is guaranteed.
tracking_urlYes
address_statusYes
document_sourceYes
first_usps_scanYesEarliest recorded individual-letter USPS scan, including acceptance: at is UTC, date is the scan’s local YYYY-MM-DD date, scan is USPS’s wording. Excludes shipment acceptance-pending and printing-partner scans. Null means no individual-letter scan is recorded, not that the letter was never mailed. Only proof_of_mailing establishes an acceptance date.
tracking_numberYes
address_as_givenYes
files_deleted_atYesUTC time the letter files were deleted, or null. After deletion, preview_url is retained for compatibility but no longer downloads a file; receipt_url is omitted. Tracking and the record stay available at letter_url.
proof_of_mailingYesThe acceptance scan records when USPS accepted the letter; null until an acceptance scan is recorded. Assistants cite date as the mailing date. This is not a postmarked receipt or a legal-status determination.
partner_checked_atYesUTC time of the last successful live tracking poll recorded by this service, even if USPS supplied no new scans. Null means no successful poll time is recorded (including test or legacy letters). A read never polls the partner; this is not a delivery or mailing time or a freshness guarantee.
acceptance_expected_byYesEastern date (YYYY-MM-DD) by whose end the acceptance scan usually appears. Present from submission while no acceptance or individual-piece network/delivery scan is recorded and next_step gives this date. Null after an individual-piece scan even if acceptance is missing; proof_of_mailing remains null. Before it ends, tell the person when to contact support; after it ends, contact support now so we can check with the printing partner and USPS.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already establish readOnly and non-destructive, but the description adds much more: 'Reading is free and changes nothing,' per-minute retry for up to a day, partner/queue delays, and careful semantic caveats (accepted ≠ bank-posted, first_usps_scan ≠ shipment receipt, partner_checked_at ≠ scan date, files_deleted_at means downloads are gone). It also explains auth mechanics and timestamp formats. This is unusually rich disclosure beyond structured fields.

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?

With a 100% schema coverage and a dedicated output schema handling field descriptions, the massive field-by-field enumeration is largely redundant, and the run-on semicolon chains hurt readability. The purpose is front-loaded, but overall it is bloated relative to what the structured data already carries, so this lands at 3.

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

Completeness4/5

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

For a status-read tool of this complexity, the definition covers auth, latency expectations, re-polling, field semantics, and deadline interpretation. One gap remains: neither parameter is required (0 required), yet the description never says what happens if both are omitted or what an invalid/expired token returns.

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 coverage is 100%, and both parameters are already fully described in the schema, including the Authorization requirement and the embedded t token. The description largely restates this, adding only a concrete letter_url example. Baseline 3 is appropriate since the schema does the heavy lifting.

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 opening sentence names a specific verb and resource — 'Read a letter's state, timeline, tracking...' — and enumerates the fields returned, so the agent knows exactly what it retrieves. It never explicitly distinguishes itself from siblings such as list_letters or cancel_letter, which keeps it at 4 rather than 5.

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 real usage context: 'read again after a minute' for a pending address_status, that address checks usually finish in seconds, and how to supply identity ('Use id with its API key, or the complete private letter_url from create_letter'). It also tells the agent what to relay ('Relay next_step', compare a user deadline against the delivery estimate). It stops short of naming when to prefer a sibling tool or any exclusion case.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources