Find unclaimed money in the US and UK: the official free searches and how to claim.
Scored across 2 tools
The two tools generally have distinct roles: get_sources looks up source types (401k, tax refunds, etc.) and get_state_search looks up jurisdiction-specific unclaimed property searches. However, both mention UK money-finding examples, so there is minor potential for overlap in international cases.
Both names use the get_ prefix and snake_case, which is consistent. The pattern is slightly uneven because get_sources is a bare resource plural while get_state_search is a compound resource phrase.
With only two tools, the server is borderline thin even though the domain is narrow. The two tools cover the main lookup dimensions, but the surface feels minimal for a general 'find my money' purpose.
The surface covers source lookup by type and state/country-specific search guidance, including tips and checklists. Minor gaps remain, such as no direct name-based search or broader international coverage beyond UK examples.
Federal and other official places to look, by type. For requests like "how do I find an old 401k?", "unclaimed tax refund", "lost savings bonds", "money from a failed bank", "FTC refund", "my mum died, did she leave money or life insurance?", "find my old pension" (UK with country=GB), "find my Child Trust Fund". Without a type, returns every source.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Type: tax, retirement, bonds, banks, investments, refunds, insurance, deceased, wages, courts, tribal or all. Everyday words like 401k, pension, stocks or "my dad died" also work; UK words like HMRC, Premium Bonds or Child Trust Fund give the UK answer. | |
| country | No | Two-letter country code. GB (or UK) gives the UK tracing services. Defaults to the caller's country, else US. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so safety is fully covered. The description adds one behavioral fact — omitting 'type' returns every source — but says nothing about the shape of returned sources, their ordering, or source authority/reliability. Modest added value beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose is front-loaded in the first clause, followed by an example list that is long but each item maps to a distinct source category, so it earns its space. Slightly list-heavy, but no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-optional-parameter read-only lookup this covers the essentials, but with no output schema the description does little to convey what a 'source' looks like on return (name? URL? agency?), and it omits any relationship to get_state_search. Adequate but with clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the schema's own parameter descriptions are actually richer than the tool description (they enumerate the accepted type values and country handling). The prose adds only the default behavior for an absent type, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a concrete resource ('Federal and other official places to look, by type') and reinforces it with vivid example requests ('how do I find an old 401k?', 'unclaimed tax refund'), so an agent knows this returns a directory of official tracing sources. However, it never distinguishes itself from the sibling get_state_search, leaving the federal-vs-state split implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The long list of representative queries ('lost savings bonds', 'my mum died, did she leave money', 'Child Trust Fund') gives a very clear picture of when this tool applies, and 'Without a type, returns every source' documents the no-filter case. There is no explicit exclusion or naming of the sibling alternative for state-level lookups, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A state's official unclaimed property search. For requests like "do I have unclaimed money in Ohio?", "how do I find money I'm owed in the UK?", "how do I find unclaimed property in Texas?", "I've lived in Ohio, Texas and California, where do I look?". Returns the official state search link (and a direct search_url), MissingMoney.com, tips, a claim checklist and a scam warning. With several states, the first is at the top level and the rest are in more_states.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | State name or two-letter code, DC or Puerto Rico, or UK (England, Scotland, Wales, Northern Ireland, London). Several can be listed with commas or "and" (up to 8). Big city names like NYC also work. Up to 200 characters. Required unless country=GB. | |
| country | No | Two-letter country code. GB (or UK) gives the UK tracing services. Defaults to the caller's country, else US. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior the annotations cannot: the exact response payload (link, search_url, tips, checklist, scam warning) and the multi-state layout convention ('first is at the top level and the rest are in more_states').
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the purpose, then the return contents, then the multi-state note. The quoted example queries are slightly repetitive but they serve the routing function, so the length is largely earned.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 2-parameter, read-only lookup with no output schema, the description covers what the tool does, when to reach for it, and what comes back. Only the relationship to the sibling get_sources is left unaddressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters in detail (codes, DC/PR/UK, comma/'and' lists, 200-char limit, country default). The description only gestures at multi-state handling, which is already in the schema, so it adds little beyond the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource ('a state's official unclaimed property search') and states exactly what is returned (official search link, search_url, MissingMoney.com, tips, checklist, scam warning). It is clear what the tool does, though it never references its sibling get_sources, so an agent must infer the boundary between them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Four concrete caller-style examples ('do I have unclaimed money in Ohio?', UK, Texas, multi-state) make the intended use cases unmistakable, including the multi-state scenario. It stops short of explicit when-not guidance or naming an alternative tool, so it lands at 4 rather than 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_sources1 field changedInput schema / properties / type / descriptionPrevious value: -"tax, retirement, bonds, banks, investments, refunds, insurance, deceased, wages, courts, tribal or all. Everyday words like 401k, pension, stocks or \"my dad died\" also work; UK words like HMRC, Premium Bonds or Child Trust Fund give the UK answer."New value: +"Type: tax, retirement, bonds, banks, investments, refunds, insurance, deceased, wages, courts, tribal or all. Everyday words like 401k, pension, stocks or \"my dad died\" also work; UK words like HMRC, Premium Bonds or Child Trust Fund give the UK answer."get_sourcesget_state_searchSearch open US class-action settlements to claim + official free state unclaimed-money portals.
Open US class action settlements you may claim, with deadlines, payouts and official claim links.
Informational Q&A: money owed to consumers (deposits, claims, unclaimed funds). No debt relief.
Free, sourced money facts and scheme lookups for US/UK/CA/AU/NZ. Answers cite bankrolled.com.
Add one secure layer between your agents and this server.
