Dated US business records before signing a quote, paying a deposit or sending money.
Scored across 3 tools
check_business and check_mover have overlapping purposes since check_mover is an alias for the mover kind, but the alias is clearly labeled and compare_businesses is distinct, so misselection is limited.
All tool names follow a consistent snake_case verb_noun pattern: check_business, check_mover, compare_businesses.
Three tools is appropriate for a service that checks and compares business records, though check_mover is a redundant alias, so the set is slightly over-specified.
The tools cover single-business checks across many kinds and multi-business comparisons, with no obvious missing operations for the stated domain.
Use this when the user names a specific US business and asks whether it is legitimate, licensed, or safe to pay, what public records exist on it, or what to check before signing a quote, paying a deposit, sending money, or paying a business that is asking them for money, such as a debt collector. Covered kinds: movers, moving brokers, auto transport, puppy breeders, debt collectors, lenders, debt-relief and credit-repair companies, mortgage servicers, financial advisors, brokerage firms, online stores, ticket resellers, timeshare exit, rental listings, and the home-service and local trades listed below. Returns dated public records, sources and one question to ask, without a verdict, score, rating or recommendation. Movers and moving brokers: FMCSA authority history, insurance filings, household-goods complaints, SAFER safety records, and other carriers in the same state with authority revocation records that share its phone number or company officers. Auto transport: FMCSA motor-vehicle cargo identity, authority, filings and safety records; household-goods complaints do not cover this kind. Puppy breeders: USDA APHIS inspection counts, dates and critical/non-critical counts; current license status and direct-item detail are unavailable. Debt-relief/credit-repair, lenders, debt collectors and mortgage servicers: CFPB complaint counts by year, product mix, response timing against the product baseline and latest complaint date. Financial advisors and brokerage firms: BrokerCheck link only; registration and disclosures are blocked by its terms on AI use. Online stores, ticket resellers, timeshare exit and rental listings: dated FTC weekly-index matches, or an explicitly bounded no-match result. Roofers, HVAC, plumbers, contractors, solar installers, garage-door services, locksmiths, towing/recovery, pest control, used-car dealers, auto repair, apartment complexes and rental/property managers: a thin layer of state lookup guidance where verified, without federal business facts. Search by business name and location or USDOT, MC, USDA license, CRD or CFPB company name. Missing kind or ambiguous identities return candidates, never a guess. Unavailable sources are labeled. US coverage only; records do not establish safety, wrongdoing or permission for every activity. No reviews, booking, payment or personal-character checks.
| Name | Required | Description | Default |
|---|---|---|---|
| mc | No | MC number. | |
| crd | No | CRD number; only used to form an official BrokerCheck link. | |
| city | No | Business city, if known; not the customer location. | |
| kind | No | Business category; omitted categories require conservative resolution. | |
| name | No | Legal or trading business name. | |
| state | No | Business US state code or full state name. | |
| usdot | No | USDOT number. | |
| cfpb_company | No | Exact company name in CFPB records. | |
| usda_license | No | USDA certificate, such as 42-A-1234. |
| Name | Required | Description |
|---|---|---|
| card | Yes | |
| kind | Yes | |
| limits | Yes | |
| status | Yes | |
| findings | Yes | |
| identity | Yes | |
| businesses | No | |
| candidates | Yes | |
| checked_at | Yes | |
| comparison | No | |
| ask_them_this | Yes | |
| sources_answered | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnly/openWorld annotations by disclosing output shape and limits: dated records plus sources, one question to ask, and explicitly no verdict, score, rating or recommendation. It also names per-kind data limits (FMCSA coverage vs household-goods complaints for auto transport, unavailable USDA license status, BrokerCheck registration blocked by terms), states that missing kind or ambiguous identity returns candidates rather than a guess, and labels unavailable sources.
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 critical trigger sentence is correctly front-loaded, but the body is a dense, run-on enumeration of per-kind data sources that is hard to scan and reads like internal documentation. The information is non-redundant, yet the single-block format obscures the few facts an agent actually needs at call time.
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 9-parameter, multi-source lookup, the description is thorough: it covers coverage limits, US-only scope, the no-verdict stance, and degraded behavior for thin kinds, and an output schema exists so return values need not be re-explained. The one missing piece is explicit sibling disambiguation with check_mover, which is material for correct tool selection.
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 every identifier (name, city, state, usdot, mc, usda_license, crd, cfpb_company, kind) is already documented in the schema. The description adds only that any of the identifiers can serve as the search key and that an omitted kind triggers conservative resolution, which is real but marginal value on top of a fully documented 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 states a specific verb+resource (retrieving public records on a named US business) and enumerates the covered business kinds, so an agent knows exactly what class of question this answers. It does not, however, disambiguate against the sibling check_mover, despite listing movers as a covered kind, leaving a real selection ambiguity.
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?
Trigger conditions are unusually explicit: use when the user names a specific business and asks about legitimacy/licensing, or before signing a quote, paying a deposit, or paying a debt collector. Exclusions are also stated (no reviews, booking, payment, personal-character checks), but neither sibling tool is named as an alternative, so the routing to check_mover vs compare_businesses is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compatibility alias for check_business with kind=movers. Returns the same dated mover records; no verdict, rating or recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| mc | No | MC number, digits with optional MC prefix. | |
| city | No | City, if known; use its own field, such as New York. | |
| name | No | Moving company's name. May be supplied without a location. | |
| query | No | Legacy free-text mover name/location or USDOT/MC number. Prefer the separate fields. | |
| state | No | Two-letter US state code or full state name, case-insensitive, if known. | |
| usdot | No | USDOT number, digits with optional USDOT prefix. |
| Name | Required | Description |
|---|---|---|
| card | Yes | |
| kind | Yes | |
| limits | Yes | |
| status | Yes | |
| findings | Yes | |
| identity | Yes | |
| businesses | No | |
| candidates | Yes | |
| checked_at | Yes | |
| comparison | No | |
| ask_them_this | Yes | |
| sources_answered | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description adds meaningful context beyond them: it returns the same records as check_business and explicitly provides 'no verdict, rating or recommendation.' That negative-capability statement is genuinely useful for setting agent expectations about the output.
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?
Two tight sentences with zero waste; the alias relationship is front-loaded and the output disclaimer follows. Nothing redundant.
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 an output schema present, return values need not be explained, and the description correctly avoids that. It covers the alias role and the no-verdict caveat; the only minor gap is not stating preference between this alias and check_business.
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 all six parameters (name, usdot, mc, query, city, state) are already documented in the schema. The description adds no parameter-level detail beyond noting the internal kind=movers mapping, 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?
States a specific role (compatibility alias for check_business with kind=movers) and the resource it returns (dated mover records), and names the sibling tool it maps onto. An agent can immediately tell what this tool is and how it differs from check_business.
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?
Calling it a 'compatibility alias' implies it exists for legacy callers and that check_business is the canonical path, but the description never explicitly says when to prefer one over the other. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when the user explicitly asks to compare public records for two to five specific businesses of the same offered kind in one city/state before signing or paying. Returns a table of the kind's record types with each business's dated sources, unavailable labels, limits and identity candidates. Covers movers, moving brokers, auto transport, puppy breeders, debt-relief/credit-repair, lenders, debt collectors, mortgage servicers, financial advisors, brokerage firms, online stores, ticket resellers, timeshare exit, rental listings and the state-guidance kinds listed by check_business. BrokerCheck data is blocked by terms; kinds without a federal net have only verified state guidance. The shared seven-second budget is divided across entries, so slow sources can remain unavailable. Does not rank businesses, pick a winner, recommend one, book anything or move money.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| kind | Yes | ||
| state | No | ||
| entries | Yes |
| Name | Required | Description |
|---|---|---|
| card | Yes | |
| kind | Yes | |
| limits | Yes | |
| status | Yes | |
| findings | Yes | |
| identity | Yes | |
| businesses | No | |
| candidates | Yes | |
| checked_at | Yes | |
| comparison | No | |
| ask_them_this | Yes | |
| sources_answered | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnly/openWorld/destructive annotations: BrokerCheck data is blocked by terms, kinds without a federal net only carry verified state guidance, and the shared seven-second budget is split across entries so slow sources may stay unavailable. It also previews the returned table's shape (dated sources, unavailable labels, limits, identity candidates), which is exactly the operational context an agent needs to set expectations.
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 usage trigger is correctly front-loaded and the closing negative list is valuable, but the long enumeration of covered industries largely duplicates the kind enum already in the schema and inflates the definition without adding selection signal.
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 comparatively complex comparison tool, the description covers the important runtime caveats (blocked sources, timeouts, no ranking) and the tool has an output schema, so return-format detail is not required. The uncovered identifiers and the exact city/state correspondence rule are the remaining minor 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?
The description conveys the semantics of entries (2-5, same kind), kind, and city/state, but does nothing for the identifier parameters (usdot, mc, crd, usda_license, cfpb_company) whose accepted forms it never explains. It also re-lists many kind values without clarifying semantics beyond the enum. With only the schema's terse property labels available, this leaves real gaps.
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?
States a specific verb (compare) plus the resource (public records) and bounds the scope: two to five businesses of the same offered kind in one city/state. This is clearly distinguishable from the single-entity siblings check_business and check_mover.
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?
Gives an explicit trigger ('when the user explicitly asks to compare') and a timing cue ('before signing or paying'), plus a clear negative list (no ranking, no winner, no booking, no money movement). It does not explicitly route the agent to check_business for the single-business case, so it stops short of naming the alternative.
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.
check_businesscheck_movercompare_businessesVerify a business before an agent pays, signs or buys: registry-cited decision and signed receipt.
Free agent identity and signed US supplier-payment decisions. Inspect first; verify portable proof.
Check a European business before you pay or sign.
Before an agent pays, get a verdict and a keepable receipt. Not insurance. Not custody.
Add one secure layer between your agents and this server.
