Search current class-action settlements and identify possible matches using structured filters.
Scored across 5 tools
Each tool has a clearly distinct purpose: dataset metadata, single-record retrieval, batch retrieval, single search, and batch search. No overlapping boundaries or potential for misselection.
All tool names follow a consistent verb_noun snake_case pattern (get_dataset_info, get_settlement, get_settlements, search_settlements, search_settlements_batch). Verbs and noun plurality are used logically and consistently.
With exactly 5 tools, the server is well-scoped for its apparent purpose of settlement searching and retrieval. Each tool fills a necessary role without redundancy, making the count ideal.
The tool surface fully covers the read-only workflow: dataset-level info, targeted retrieval (single and batch), and search (single and batch). No obvious gaps for the domain, as update/create/delete operations are not implied by the server's purpose.
Return source, license, freshness, counts, and hosted aggregate metrics.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds the specific fields returned, which is useful but does not go beyond what annotations plus output schema would imply.
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?
A single, front-loaded sentence that names all key return contents. No wasted 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?
The tool is simple (no params, read-only, idempotent) and has an output schema, so the description does not need to explain return values. The description names the key data categories and is complete for this scope.
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 tool has zero parameters, so the schema is empty and there is nothing to explain. Baseline for 0 params is 4, which 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 uses a specific verb 'Return' and names precise resource components (source, license, freshness, counts, hosted aggregate metrics). This clearly distinguishes it from sibling settlement-related tools.
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?
No explicit when-to-use or alternative guidance is provided. However, the description clearly implies it is for dataset metadata retrieval, and sibling names confirm it is separate from settlement operations, so usage context is indirectly clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the complete stored record and official source links for one settlement ID produced by a search.
| Name | Required | Description | Default |
|---|---|---|---|
| settlement_id | Yes | Exact settlement identifier returned by a search. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context by stating the returned data is the 'complete stored record' and includes 'official source links,' which goes beyond the schema.
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?
A single, front-loaded sentence communicates the core action, scope, and output without wasted words. Every phrase contributes meaning.
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 the tool is a low-complexity single-parameter retrieval, the description, rich annotations, and output schema cover everything needed for an agent to select and call it correctly.
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 only parameter settlement_id is already described as the 'Exact settlement identifier returned by a search.' The description reinforces this but adds no significant new meaning beyond the 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 uses a specific verb and resource: 'Return the complete stored record and official source links for one settlement ID produced by a search.' It clearly distinguishes this tool from siblings like search_settlements and get_settlements by focusing on retrieving a single, already-known settlement record.
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?
It clearly implies usage after a search has produced a settlement ID, saying 'one settlement ID produced by a search.' However, it does not explicitly state when not to use it or name alternatives, so it misses the highest tier of guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return complete stored records and official source links for up to 20 settlement IDs produced by search.
| Name | Required | Description | Default |
|---|---|---|---|
| settlement_ids | Yes | Settlement identifiers returned by search to retrieve together. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read-only nature is clear. The description adds that it returns 'complete stored records and official source links', which indicates a richer response than a summary. This is useful context beyond annotations. No contradiction exists.
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 a single concise sentence, front-loaded with the primary purpose, and includes key constraints (up to 20 IDs). There is zero waste; every word contributes 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 one parameter (fully covered by schema), strong annotations, an output schema present, and a clear description, the tool is well documented. The description explains the use case ('produced by search') and the batch limit, which is sufficient. Minor gap: it doesn't mention error behavior or what happens if an ID is invalid, but given the presence of an output schema, this is acceptable.
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 parameter 'settlement_ids' is well documented already. The description adds that these are 'produced by search' and 'to retrieve together', which reinforces the batch context, but it doesn't add new semantics beyond the schema's description. 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 clearly states the tool returns complete stored records and official source links for up to 20 settlement IDs produced by search. The verb 'Return' is specific, the resource is 'settlements', and the scope ('up to 20') is defined. However, it doesn't explicitly distinguish from sibling 'get_settlement' (singular), though the pluralization and 'up to 20' partially imply a batch operation.
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 says 'produced by search', which implies this tool is used after search results are obtained, providing a context. However, it doesn't explicitly state when-not-to-use or mention alternatives like 'get_settlement' for single-record retrieval. The guidance is minimal but not misleading.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search one settlement angle using logical AND keywords and structured status, type, state, proof, and deadline filters. Status defaults to open. Results include source metadata and quality flags.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum records returned, from 1 to 50. | |
| state | No | Optional two-letter US postal abbreviation, such as CA. | |
| status | No | Public lifecycle filter: open or upcoming. Defaults to open. Upcoming records are not yet claimable and must be presented as a separate watchlist. | open |
| keywords | No | Required logical-AND terms for specific companies, brands, products, employers, services, or incidents. Use separate queries for alternatives and settlement_type for taxonomy. | |
| deadline_after | No | Include deadlines on or after this ISO 8601 date. | |
| proof_required | No | Whether proof is required: yes, no, or unknown. | |
| deadline_before | No | Include deadlines on or before this ISO 8601 date. | |
| settlement_type | No | Exact settlement taxonomy filter. Prefer this over keywords for type concepts such as data breaches, privacy, refunds, financial fees, or consumer products. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool is read-only, idempotent, and non-destructive, so the description correctly focuses on additional behavior: it reveals the default status filter ('Status defaults to open') and the content of results ('Results include source metadata and quality flags'). These details go beyond the structured annotations and add value for the agent.
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 sentences, front-loaded with the core action and constraints, and every part adds value—scoping (one angle), filter types, default status, and result contents. No fluff 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 search tool with 8 optional parameters and an output schema, the description covers the essential aspects: purpose, filters, default, and result summary. It does not detail response format (covered by output schema) or pagination, but those are not critical for initial selection. It adequately informs an agent about what to expect.
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 each parameter already has a description. The tool description reinforces the AND semantics for keywords and lists filter categories, but these are already present in the parameter descriptions (e.g., 'Required logical-AND terms' for keywords). It adds little new meaning beyond the schema, placing it at the baseline for full 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 a specific action (search) on a specific resource (settlements) and adds the scoping constraint 'one settlement angle' with logical AND keywords, distinguishing it from the batch sibling search_settlements_batch. The filter categories (status, type, state, proof, deadline) are enumerated, making the tool's purpose unambiguous.
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 implies usage via 'one settlement angle' and the keyword parameter description in the schema suggests using separate queries for alternatives, but it does not explicitly state when to prefer this tool over siblings or when not to use it. It lacks direct exclusions or named alternatives, leaving the agent to infer from the name and context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run up to 50 independent settlement searches and deduplicate records across queries. Results include matched_query_indices, and executed_query_count reports the number of searches performed. Use when several unrelated search angles should be evaluated together.
| Name | Required | Description | Default |
|---|---|---|---|
| queries | Yes | Independent settlement searches. Each query retains logical-AND keyword semantics; unrelated alternatives belong in separate query objects. | |
| max_total_results | No | Maximum unique settlement records returned across the whole batch after cross-query deduplication. This caps output, not the number of independent searches performed. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint: true, destructiveHint: false, openWorldHint: false. The description adds: it deduplicates records across queries Eq. and reports executed_query_count. However, it does not mention partial-failure behavior, query-level limits, or what happens when max_total_results cap is hit. With annotations carrying the read-only safety profile, the description adds moderate behavioral context (deduplication and count reporting) but not rich detail on failure modes or output shape.
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?
Three sentences, no fluff easchjs. Clearly explains batch capability, result metadata, and when to use. Efficient.
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 batch tool, the description explains the core behavioral traits (deduplication, count reporting, cap) and when to use it. It doesn't describe result structure (e.g., grouped by query) but given the input schema richness and readOnly annotations, this is a solid comprehensive description. Could mention parallel independent behavior more, but the queries array description in schema covers it. Score 4.
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 of parameters is high (all params documented in schema), so description adds limited incremental value. The description clarifies that max_total_results caps output but not the number of searches, which is a useful clarification that goes slightly beyond the schema. For the queries array parameter, it already says 'Independent settlement searches' and retains the AND semantics in the schema. Description adds dedup context for results but not parameter-level details. Baseline 3 is appropriate with the slight boost for clarifying max_total_results.
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?
Description accurately conveys purpose: run up to 50 settlement searches in one batch, dedupe results. It identifies the verb (search), resource (settlements), and mode (batch), clearly distinguishing itself from a single settlement search. It lacks an explicit sibling name reference, but the verb+resource+scope structure is clear enough to position it.
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?
Description tells when to use: 'several search angles should be evaluated together' and the annotation 'openWorldHint: false' reinforces constrained usage. Explicitly contrasts with a single-search tool by mentioning independent queries and dedup. It does not state 'when NOT to use', but provides strong positive guidance and boundary (up to 50 queries) so an agent can decide to route batch vs single search.
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_settlements2 fields changedInput schema / properties / proof_required / anyOfPrevious value: -[
- {
- "enum": [
- "yes",
- "no",
- "optional",
- "varies",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "yes",
+ "no",
+ "unknown"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / proof_required / descriptionPrevious value: -"Exact proof requirement: yes, no, optional, varies, or unknown."New value: +"Whether proof is required: yes, no, or unknown."search_settlements_batch2 fields changedInput schema / $defs / SearchQuery / properties / proof_required / anyOfPrevious value: -[
- {
- "enum": [
- "yes",
- "no",
- "optional",
- "varies",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "yes",
+ "no",
+ "unknown"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / $defs / SearchQuery / properties / proof_required / descriptionPrevious value: -"Exact proof requirement: yes, no, optional, varies, or unknown."New value: +"Whether proof is required: yes, no, or unknown."search_settlements2 fields changedInput schema / properties / proof_required / anyOfPrevious value: -[
- {
- "enum": [
- "yes",
- "no",
- "optional",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "yes",
+ "no",
+ "optional",
+ "varies",
+ "unknown"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / proof_required / descriptionPrevious value: -"Exact proof requirement: yes, no, optional, or unknown."New value: +"Exact proof requirement: yes, no, optional, varies, or unknown."search_settlements_batch2 fields changedInput schema / $defs / SearchQuery / properties / proof_required / anyOfPrevious value: -[
- {
- "enum": [
- "yes",
- "no",
- "optional",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "yes",
+ "no",
+ "optional",
+ "varies",
+ "unknown"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / $defs / SearchQuery / properties / proof_required / descriptionPrevious value: -"Exact proof requirement: yes, no, optional, or unknown."New value: +"Exact proof requirement: yes, no, optional, varies, or unknown."get_settlements1 field changedInput schema / properties / settlement_ids / descriptionPrevious value: -"Settlement identifiers to retrieve together. Use this for every finalist from a broad scan before composing the final answer."New value: +"Settlement identifiers returned by search to retrieve together."search_settlements3 fields changedInput schema / properties / keywords / descriptionPrevious value: -"Required AND terms for specific companies, brands, products, employers, or incidents. Do not put a settlement-type label here when settlement_type applies. For broad eligibility scans, make multiple separate searches covering plausible aliases, related brands, parent companies, services, purchases, fees, incidents, and eligibility-relevant demographic angles."New value: +"Required logical-AND terms for specific companies, brands, products, employers, services, or incidents. Use separate queries for alternatives and settlement_type for taxonomy."Input schema / properties / status / descriptionPrevious value: -"Claim lifecycle: open, closed, payment, unknown, or all. Defaults to open. Use all only when intentionally including non-open lifecycle states."New value: +"Public lifecycle filter: open or upcoming. Defaults to open. Upcoming records are not yet claimable and must be presented as a separate watchlist."Input schema / properties / status / enumPrevious value: -[
- "open",
- "closed",
- "payment",
- "unknown",
- "all"
-]New value: +[
+ "open",
+ "upcoming"
+]search_settlements_batch3 fields changedInput schema / $defs / SearchQuery / properties / status / descriptionPrevious value: -"Claim lifecycle; defaults to open. Use all only when intentionally searching non-open lifecycle states as well."New value: +"Public lifecycle filter: open or upcoming. Defaults to open. Upcoming records are not yet claimable and belong in a separate watchlist."Input schema / $defs / SearchQuery / properties / status / enumPrevious value: -[
- "open",
- "closed",
- "payment",
- "unknown",
- "all"
-]New value: +[
+ "open",
+ "upcoming"
+]Input schema / properties / queries / descriptionPrevious value: -"Independent settlement searches. Use one query object per unrelated company, product, alias, alternative term, or search angle. Keywords inside each object still use logical AND."New value: +"Independent settlement searches. Each query retains logical-AND keyword semantics; unrelated alternatives belong in separate query objects."search_settlements4 fields changedInput schema / properties / status / anyOfRemoved value: -[
- {
- "enum": [
- "open",
- "closed",
- "payment",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]Input schema / properties / status / descriptionPrevious value: -"Claim lifecycle: open, closed, payment, or unknown. Defaults to open. Pass null to include every lifecycle status."New value: +"Claim lifecycle: open, closed, payment, unknown, or all. Defaults to open. Use all only when intentionally including non-open lifecycle states."Input schema / properties / status / enumAdded value: +[
+ "open",
+ "closed",
+ "payment",
+ "unknown",
+ "all"
+]Input schema / properties / status / typeAdded value: +"string"search_settlements_batch4 fields changedInput schema / $defs / SearchQuery / properties / status / anyOfRemoved value: -[
- {
- "enum": [
- "open",
- "closed",
- "payment",
- "unknown"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
-]Input schema / $defs / SearchQuery / properties / status / descriptionPrevious value: -"Claim lifecycle; defaults to open. Use null for all statuses."New value: +"Claim lifecycle; defaults to open. Use all only when intentionally searching non-open lifecycle states as well."Input schema / $defs / SearchQuery / properties / status / enumAdded value: +[
+ "open",
+ "closed",
+ "payment",
+ "unknown",
+ "all"
+]Input schema / $defs / SearchQuery / properties / status / typeAdded value: +"string"get_dataset_infoget_settlementget_settlementssearch_settlementssearch_settlements_batchSearch open US class-action settlements to claim + official free state unclaimed-money portals.
Search public U.S. federal litigation: companies, cases, dockets and document metadata.
Simplified lookup of a person's or company's lawsuits from the CPF or CNPJ. Platform-hosted, no cred
Search US federal and state court records through CourtListener and the RECAP archive
Add one secure layer between your agents and this server.
