MyLastWill

Write a will (free)

create_will

Read-onlyIdempotent

Draft a complete U.S. last will and testament, optionally with charitable gifts to causes the person chooses. Use when someone wants to make, write or update a will. Interview the person first and pass only facts they gave you; never invent names. Returns the will text, a state-specific signing checklist, a plain-English summary of who inherits, and warnings to resolve before signing. Not legal advice; wills are not produced for Louisiana or North Carolina residents (gift wording is returned instead).

Input Schema

Name	Required	Description
`fund`	No	Only for giving_method named_fund: a foundation-style named fund that keeps giving.
`causes`	No	Causes that receive the charitable gift, with each one's share. Use list_causes for the built-in causes, or describe your own.
`family`	No	Family and who inherits the part of the estate that does not go to causes.
`person`	Yes	The person making the plan.
`backstop`	No	If no one named in the will survives, give everything to the causes instead of to unnamed relatives or the state. Off unless the person explicitly wants it.
`executor`	No	Full name of the executor (personal representative).
`guardian`	No	Guardian for minor children.
`giving_method`	No	research_guided: the executor gives each cause's share to effective charities working on it, guided by MyLastWill.org research (default). named_charities: give to the specific charities listed under each cause. named_fund: create a named legacy fund (see fund).
`backup_executor`	No
`backup_guardian`	No
`estate_estimate`	No	Rough value in USD of property passing under the will (exclude retirement accounts, life insurance and anything with a named beneficiary or joint owner). Used only for dollar estimates.
`has_living_trust`	No	True if the person has a revocable living trust (a new will may affect it).
`minor_money_manager`	No	Person to manage property that minor children inherit (optional).
`charitable_share_percent`	No	Percentage of the estate that goes to causes. 0 for none.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the exact return payload (will text, state-specific signing checklist, plain-English inheritance summary, pre-signing warnings), the non-legal-advice framing, and the significant jurisdiction limitation where gift wording is returned instead of a will. readOnlyHint=true is consistent with a tool that only drafts text and writes nothing.

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?

Four tight sentences, front-loaded with the purpose, then the trigger, then the critical interviewing constraint, then return values and the jurisdiction caveat. Every sentence adds information an agent needs before invoking the tool.

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 14-parameter nested tool with no output schema, the description explains outcomes and the one hard failure mode (LA/NC). The main remaining gap is routing guidance versus add_charity_to_existing_will and get_state_will_requirements, which an agent must infer.

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 86% and the nested schemas document causes, giving_method, and family plan in detail, so the schema carries the parameter burden. The description mentions the charitable-gift option but adds no field-level meaning (e.g., how causes/percent scaling or backstop interact) beyond what the schema already says.

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 artifact ('Draft a complete U.S. last will and testament') plus the optional charitable-gift variant. This is clearly distinguishable from siblings like add_charity_to_existing_will (complete new draft vs. amending) and get_bequest_language (clause text vs. full document).

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?

Explicit trigger ('Use when someone wants to make, write or update a will') plus a concrete pre-call instruction to interview the person and never invent names. It also carves out the LA/NC exception. It stops short of naming sibling alternatives such as add_charity_to_existing_will for someone who already has a will.

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

All MyLastWill 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?