Search open US class-action settlements to claim + official free state unclaimed-money portals.
Scored across 2 tools
The two tools have completely distinct purposes: one searches active class-action settlements, the other provides links to state unclaimed property portals. There is no ambiguity between them.
Both tool names use snake_case and are descriptive of their functions (search_settlements, unclaimed_money_portal), maintaining a consistent style.
With only 2 tools, the server feels thin for a domain like 'found money.' It covers two basic needs but lacks auxiliary tools (e.g., for claims or direct searches), though the count is not extreme.
The server only provides search for settlements and portal links for unclaimed property, omitting any tool for actual claims or direct searches within state databases. Users must leave the MCP to complete even basic workflows.
Search currently-open US class-action settlements you may be able to claim for free. Filter by keyword (company/brand), category (e.g. data-breach, privacy, junk-fees), and whether proof is required. Returns each settlement's payout, claim deadline, days-left, proof requirement, category, and official claim URL. Sorted by soonest deadline. Use to find money a user may be owed.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 20, max 100). | |
| keyword | No | Company/brand or topic to match, e.g. 'Equifax' or 'breach'. | |
| category | No | Category slug filter, e.g. 'data-breach', 'privacy', 'junk-fees', 'auto-vehicle'. | |
| noProofOnly | No | If true, only return settlements that appear to need no purchase proof. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that only currently-open settlements are returned, sorted by soonest deadline, and lists exact return fields (payout, deadline, days-left, etc.). This gives good behavioral insight for a search tool. No mention of destructive behavior.
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?
Four sentences with no redundancy: first states purpose and scope, second explains available filters, third specifies return data and sorting, fourth gives a concrete use case. Every sentence adds value.
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?
With no output schema, the description explains return fields and sorting. It covers filters and purpose. Missing details like pagination or error handling, but for a straightforward search tool it is sufficiently complete.
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 coverage is 100%, so parameters are already documented. The description adds value by explaining that 'keyword' matches company/brand, 'category' uses slugs like 'data-breach', and 'noProofOnly' filters by proof requirement. It does not mention 'limit' but that is covered by schema.
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 clearly states the verb 'Search' and the resource 'currently-open US class-action settlements'. It specifies the scope (US, class-action, free) and distinguishes from the sibling tool 'unclaimed_money_portal' by focusing on settlements specifically.
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 description includes 'Use to find money a user may be owed' as a usage guideline. It implies when to use (when looking for free, open settlements) but does not explicitly state when not to use or compare with the sibling tool. The context is clear but lacks explicit alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the official, free unclaimed-property (unclaimed money) search portal for a US state plus the national NAUPA/missingmoney.com link. Use to direct someone to where they can search for forgotten bank accounts, refunds, etc.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | State name or 2-letter code, e.g. 'Texas' or 'TX'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks behavioral details such as return format, authentication requirements, rate limits, or side effects. For an unannotated tool, this is a significant gap.
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?
The description is two concise sentences that immediately state the purpose and use case, with no unnecessary words.
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?
Given no output schema or annotations, the description does not specify what the tool returns (e.g., a URL, HTML page, or structured data). While the purpose is clear, an agent lacks full context on how to process the result.
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?
The schema covers the single parameter 'state' with full description. The description adds minimal value by mentioning 'US state' and the national link, but the schema already explains the parameter sufficiently, meeting the baseline for 100% coverage.
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 clearly states the tool retrieves official unclaimed property search portals for US states and the national NAUPA/missingmoney.com link, effectively differentiating from sibling tool 'search_settlements' which handles settlements.
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 description explicitly says 'Use to direct someone to where they can search', providing a clear usage scenario. It does not explicitly state when not to use or compare to sibling, but the purpose naturally excludes settlement searches.
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.
search_settlementsunclaimed_money_portalSearch current class-action settlements and identify possible matches using structured filters.
Find evidence-backed U.S. free trials and savings; public benefits are available by explicit scope.
Informational Q&A: money owed to consumers (deposits, claims, unclaimed funds). No debt relief.
Search verified-open US grants (federal, state, foundation). Read-only MCP for AI agents.
Add one secure layer between your agents and this server.
