Find legal companies, retrieve registry profiles and verify company facts with source evidence.
Scored across 3 tools
Each tool targets a distinct action and resource: search_companies finds ranked matches, get_company_profile retrieves a profile by opaque ID, and verify_company_claims compares and preserves claim evidence. The descriptions clearly differentiate their purposes, with no overlapping functionality that would confuse an agent.
All three tool names follow a consistent verb_noun pattern in snake_case: get_company_profile, search_companies, verify_company_claims. The singular/plural noun variations (company vs companies) are natural and do not break the predictable convention.
Three tools cover the core workflow of searching, retrieving, and verifying company claims, which is well-scoped for a focused verification service. However, the count sits at the lower bound of typical ranges and may feel slightly thin if additional lifecycle operations are expected.
The surface handles company search, profile retrieval, and claim verification with optional monitoring, but it lacks dedicated tools to retrieve preserved proof records or manage monitoring (e.g., list or stop monitored claims). These are notable gaps that could force agents to work around the available operations.
Retrieve a CompanyProof company profile and enrichment payload by the opaque company ID returned from search_companies. This read-only operation requires an active CompanyProof evaluation or paid plan and live account access, and consumes one shared claim credit.
| Name | Required | Description | Default |
|---|---|---|---|
| company_id | Yes | Opaque CompanyProof company ID returned by search_companies. |
| Name | Required | Description |
|---|---|---|
| profile | Yes | |
| company_id | Yes | |
| enrichment | Yes | |
| section_status | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses a paid-plan/evaluation prerequisite, a live-account-access requirement, and a concrete cost of one shared claim credit. That is exactly the kind of context annotations cannot express.
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 sentences, no filler, with the core action and the credit cost both stated up front. Every clause carries information the agent needs.
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?
An output schema exists, so return values need not be explained. Prerequisites, cost, and the ID source are all covered, leaving nothing material missing for a single-parameter read tool.
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% and the parameter already documents itself as an opaque ID returned by search_companies. The description restates the same information without adding format, validation, or sourcing detail beyond the schema, so the baseline 3 applies.
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?
Specific verb (Retrieve) plus resource (CompanyProof company profile and enrichment payload) and a keying mechanism (opaque company ID). It also implicitly distinguishes itself from search_companies by naming that tool as the source of the ID.
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 establishes the correct usage context by tying the input to search_companies, so an agent knows this is a follow-up call. It does not, however, state when not to use it or name verify_company_claims as an alternative for a different need.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find ranked CompanyProof company matches by name, registration number, VAT/tax identifier or ticker, optionally narrowed by subdivision and city/state. This read-only operation requires an active CompanyProof evaluation or paid plan and live account access, and consumes one shared claim credit.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| companies | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety traits (readOnly, idempotent, openWorld, non-destructive). The description adds meaningful non-annotation context: it requires an active evaluation or paid plan and live account access, and consumes one shared claim credit. This is valuable behavioral disclosure beyond the structured 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?
Two sentences, front-loaded with the core purpose followed by access and cost constraints. Every sentence earns its place with no redundant or vague phrasing.
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 rich schema, annotations, and output schema, the description covers purpose, access requirements, and cost. It lacks explicit guidance on routing between this and sibling tools, which is the main remaining gap for an agent selecting among related operations.
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 has full description coverage for all parameters, so the description need not explain syntax. The context reports zero top-level parameters, which sets the baseline at 4. The description lists supported identifier types, but that information is already present in the schema variants.
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 and resource: 'Find ranked CompanyProof company matches' by multiple identifier types. It clearly describes the search operation, but does not explicitly differentiate it from sibling tools like get_company_profile or verify_company_claims.
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 provides prerequisites (active evaluation/paid plan, live account access) and cost (one shared claim credit), which implies when the tool is usable. However, it gives no explicit guidance on when to choose this search over alternatives such as get_company_profile or verify_company_claims.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a company, compare supported claims with current company evidence, preserve a proof record, and optionally monitor verified claims for change. This call consumes normal CompanyProof claim credits and writes to the account evidence ledger.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| claims | Yes | |
| company | Yes | |
| summary | Yes | |
| proof_id | Yes | |
| latency_ms | Yes | |
| monitoring | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the agent already knows this is a mutating, non-idempotent external call. The description goes beyond that by disclosing that it consumes CompanyProof claim credits, writes to the account evidence ledger, preserves a proof record, and that monitoring requires an eligible live key — real side-effect and prerequisite context not present in 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?
Two sentences, front-loaded with the core action sequence followed by cost/side-effect disclosure. No filler, though the four-clause first sentence is denser than it needs to be.
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 a full output schema and 100% schema coverage, the description does not need to explain return values. It covers the pipeline, the credit consumption, the ledger write and the monitoring prerequisite, leaving little an agent needs before calling it.
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%, with every parameter (message-style answer, structured claims, company object, monitor, idempotency_key) fully documented in the schema, so the baseline is 3. The description adds no parameter format or mutual-exclusivity detail beyond what the schema already carries.
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 verb chain (resolve, compare, preserve, monitor) against a clear resource (company claims), so an agent knows this verifies claims rather than merely fetching a profile. It does not explicitly contrast itself with get_company_profile or search_companies, but the 'compare supported claims with current evidence' framing is distinctive enough to separate it from a plain lookup.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no mention of the sibling tools. The only conditional hint is 'optionally monitor verified claims for change', which describes a feature rather than routing the agent between alternatives.
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_company_profilesearch_companiesverify_company_claimsSearch company records, officers, ownership, group structures and financials with provenance.
Background check any company in the world: registration, executives, courts and finances.
Verified company profiles, financials, ownership, registry records and business contacts.
Search and verify 360K+ business entities with trust scores and W3C credentials.
Add one secure layer between your agents and this server.
