Letter IRL

Change the stationery

set_stationery

Idempotent

Change the stationery of a previewed letter without previewing it again: classic (a plain page), monogram (initials in a ring), botanical (a line-drawn sprig), celebration (confetti with an optional headline), typewriter (typed in a monospace face) or handwritten (a handwriting face on faint ruled lines). Give the draftId from the preview and stationery, with monogram and headline as the letter previews take them: each call states them afresh, so a headline is kept only when given again. The page is drawn again, and the choice is remembered for the next letter preview.

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": {
      "draftId": "<draftId>",
      "stationery": "<stationery>"
    },
    "name": "set_stationery"
  }
}

Input Schema

Name	Required	Description
`draftId`	Yes	The draftId from a letter preview
`headline`	No	Optional, for the celebration stationery only: a short line printed large above the letter, such as "Happy Birthday, Sam!". It must fit on one line, and takes three of the page's lines; leave it out for confetti alone.
`monogram`	No	Optional, for the monogram stationery only: the initials to print, one to three letters, such as "JMS". Leave it out to use the initials of the return address's name.
`stationery`	Yes	The stationery to draw the letter in: classic, a plain page; monogram, initials in a ring; botanical, a line-drawn sprig; celebration, confetti with an optional headline; typewriter, the letter typed in a monospace face, which fits fewer words on the page; or handwritten, the letter in a handwriting face on faint ruled lines, which has no Greek, Hebrew or Vietnamese. Each but classic prints the date at the top right.

Output Schema

Name	Required	Description
`pages`	No	Present only for a letter of more than one page: the pages it prints on, both sides of the paper. No letter pack or gift letter pays for it; it is paid with Pay & Send.
`draftId`	Yes
`message`	Yes
`canSendNow`	Yes	Whether the balance or a gift letter pays for the letter as it is now: a restyle can change its pages, and so its price
`stationery`	Yes	The stationery the letter is now drawn in, with the date line, initials and headline it prints
`mailService`	No	With the terms, for a letter that is certified mail now, and for a sent letter that went by it: which service. Absent beside the delivery words: ordinary mail
`deliveryClass`	No	With the terms, for a letter that is certified mail or while certified mail is offered, and for a sent letter: how it is delivered, as a new preview would say it. A card draws it on its Delivery line
`contentVersion`	No	The version of this mail as it is now: send it with the send, so what is mailed is what the person saw
`sendEligibility`	Yes
`reasonCannotSend`	No
`deliveryDisclaimer`	No	With it, the words that qualify the delivery
`contentVersionBefore`	No	The version of this mail the change was made to: for the preview card, which takes contentVersion only when this is the version it shows

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare non-destructive, idempotent, closed-world mutation, so the bar is for extra context — and the description delivers the non-obvious part: monogram and headline are not persisted, 'each call states them afresh, so a headline is kept only when given again,' while the page is redrawn and the choice persists to the next preview. It also discloses practical side effects an agent cannot infer elsewhere: typewriter fits fewer words, handwritten lacks Greek/Hebrew/Vietnamese, and each non-classic style prints the date top-right.

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?

Front-loaded with the action and the 'without previewing it again' hook, and every clause carries information (style list, draftId source, non-sticky params, redraw/persistence). It is dense and slightly run-on in the enumerations, but nothing is filler.

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?

For a 4-param, non-destructive update with an output schema available for return values, the description covers everything an agent needs: prerequisites (draftId from preview), persistence semantics, per-option visual and typographic constraints, and optional-parameter behavior. Nothing material is left to inference.

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 genuine meaning beyond the schema: the draftId must come from a preview, and crucially that headline and monogram must be re-supplied on every call or they are dropped — a stateful rule absent from the property descriptions. The per-style glosses reinforce the enum without merely restating it.

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?

States a specific verb and resource ('change the stationery of a previewed letter') plus the key scope distinction from the preview siblings: it acts on an already-previewed letter 'without previewing it again.' It even enumerates the six stationery values with a visual gloss for each, so an agent can tell exactly what this changes versus quote_and_preview_letter or set_postcard_style.

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?

Clearly frames the usage context — it requires a draftId that came from a letter preview, and it exists specifically to avoid a re-preview. It also states a forward-looking consequence ('the choice is remembered for the next letter preview'). It stops short of naming quote_and_preview_letter as the alternative when no draft exists, so it is not a full when/when-not statement.

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

All Letter IRL tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?