Skip to main content
Glama

Tribute Paper

Write an obituary

write_obituary
Read-onlyIdempotent

Drafts an obituary from details the family gives, the same as Tribute Paper's free obituary writer. Returns three drafts: a traditional obituary (for a funeral home website or newspaper), a warmer personal one, and a short death notice, each with its word count. It never invents anything: a sentence appears only when its detail was given. Ask the family gently for what they'd like included first (the full name and pronoun are needed; dates, family, work, what they loved and the service details make it fuller). Give dates as YYYY-MM-DD.

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": {
      "full_name": "<full_name>",
      "pronoun": "<pronoun>"
    },
    "name": "write_obituary"
  }
}

Input Schema

NameRequiredDescriptionDefault
workNoTheir work, in the family's words, e.g. "worked as a school librarian for 34 years".
faithNoTheir faith or community, e.g. "was a lifelong member of Hillside Lutheran Church".
lovedNoWhat they loved most, e.g. "summers at the family cabin".
regionNoWhere it will be read, which sets how dates and times are written: us (United States), ca (Canada), uk (United Kingdom or Ireland), au (Australia or New Zealand).us
servedNoMilitary or community service, e.g. "served in the U.S. Navy during the Korean War".
spouseNoTheir husband, wife or partner's full name.
parentsNoTheir parents' names, e.g. Carl and Ruth Halvorsen.
passingNoHow they passed, only if the family wants it said: peacefully, suddenly, long-illness, short-illness.
pronounYesThe pronoun to use for the person who died. Ask the family rather than guessing.
known_asNoThe name they went by, if different, e.g. Peggy.
donationsNoA charity for gifts in their memory, e.g. "the Lake Superior Literacy Project".
full_nameYesTheir full name, e.g. Margaret Ellen Lindgren.
interestsNoWhat they enjoyed, e.g. "quilting, long walks by the lake, the Sunday crossword".
residenceNoWhere they lived, e.g. Duluth, Minnesota.
birth_dateNoDate of birth.
death_dateNoDate of passing.
gatheringsNoVisitation, burial or reception, in the family's words.
rememberedNoWhat they will be remembered for, e.g. "her patience and her blueberry pie".
birth_placeNoWhere they were born.
death_placeNoWhere they died, e.g. "at home" or a hospital's name.
preceded_byNoWho died before them, one per line or separated by semicolons.
spouse_roleNoWhat the spouse was to them: husband, wife or partner.
survived_byNoWho survives them besides the spouse (a living spouse is added from "spouse"), one per line or separated by semicolons, e.g. "her children, Karen (Mark) Olson and David Lindgren; five grandchildren".
funeral_homeNoThe funeral home making the arrangements.
married_yearNoThe year they married.
service_cityNoThe town or city of the service.
service_dateNoThe date of the service.
service_kindNoThe kind of service: funeral, memorial, celebration (celebration of life), mass (funeral Mass), graveside.funeral
service_timeNoThe time of the service.
service_venueNoWhere the service will be, e.g. Hillside Lutheran Church.
spouse_livingNofalse if the spouse died before them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Despite annotations already covering readOnly/idempotent/non-destructive, the description adds substantive behavior: it always returns three differently-styled drafts with word counts, and it enforces a strict no-invention rule where a sentence appears only if the supporting detail was supplied. That grounding constraint is exactly the kind of trait an agent cannot infer from the annotations or schema.

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?

Four sentences, front-loaded with purpose and output shape, then intake guidance, then the grounding rule, then the date format. The clause "the same as Tribute Paper's free obituary writer" is light promotional framing that adds little, but nothing else is wasted.

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?

With 31 parameters and no output schema, the description carries the return-value burden and does so by naming the three drafts and their word counts, plus the no-invention guarantee. It does not mention the region parameter's effect on how dates and times are rendered in output, which is the one notable gap for a tool of this complexity.

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% with per-field examples and enums, so the schema does the heavy lifting. The description only adds that full name and pronoun are required and to ask rather than guess at the pronoun, and repeats the YYYY-MM-DD format already encoded in the date patterns — minimal meaning beyond structured data, so baseline 3 applies.

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 first sentence gives a specific verb and resource ("Drafts an obituary from details the family gives") and the second specifies the exact output: three drafts — traditional, warmer personal, and short death notice — each with a word count. The resource is clearly distinct from the sibling write_eulogy without needing to name it.

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 concrete intake guidance: ask the family gently what they'd like included, with full_name and pronoun as the minimum and dates, family, work, loves and service details as enrichment. There is no explicit when-to-use versus write_eulogy or other siblings, so it stops short of full routing guidance.

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