Free: select by canonical intent, brandless problem state or plain-language problem query, including honest negative selection; no source call, charge or settlement.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| intent_id | No | ||
| problem_state | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds useful context by stating that the tool makes no source call, incurs no charge, and supports honest negative selection. This clarifies the behavioral and cost profile beyond the 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?
The description is a single, dense sentence with no fluff, and the selected input modes are listed in a parallel structure. The leading 'Free:' is ambiguous and slightly confusing, detracting from clarity, but overall it is highly compact.
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 has three mutually exclusive parameter modes and important behavioral claims ('free', 'honest negative selection'), yet the description does not explain what the response contains, what 'honest negative selection' means, or which mode should be preferred. Given the large sibling set and absent output schema, the description is under-specified for confident use.
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 provides only parameter names with no descriptions, so the parameter semantics depend entirely on this description. It maps intent_id to 'canonical intent', problem_state to 'brandless problem state', and query to 'plain-language problem query', also noting negative selection. This gives meaning to all three parameters, though without formats or examples.
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 verb ('select') and the resource (canonical intent, problem state, or plain-language query), so it is not a tautology. However, 'resolve_agent_intent' as a purpose is never explicitly defined; 'Free:' is ambiguous and the description does not make clear what resolution implies or returns, so it is only a vaguely useful purpose statement.
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 hints at when the tool is relevant ('free', 'no source call, charge or settlement') but gives no explicit guidance on when to choose this tool over its many siblings, such as resolve_legal_entity or decide. There is no when-not guidance or alternative routing, so an agent must infer the intended use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools appear to address the same action with only country or payment-model differences, such as company_check/run_uk_company_check, approve_supplier/approve_uk_supplier, authorize_payment/run_uk_payment_authorization, and screen_restricted_party/screen_restricted_business_party. Even with descriptions, an agent will struggle to pick the intended tool reliably.
Naming mixes bare global verbs (company_check, approve_supplier, authorize_payment) with UK-prefixed variants (run_uk_company_check, approve_uk_supplier, authorize_uk_business_payment), plus free-form names like counterfactual, preflight, quote, and capabilities. There is no single consistent verb_noun or country-modifier convention across the set.
46 tools is far beyond the typical well-scoped MCP surface, and the set carries heavy duplication through global/UK/free/paid variants. While the domain may justify multiple country-specific operations, the tool count itself will overwhelm agents and make selection harder.
The server covers the main compliance lifecycle well: discovery (capabilities, preflight, quote, resolve_agent_intent), verification, supplier approval, payment authorization, invoice matching, passport issuance/refresh, and verification receipts. Minor gaps exist around explicit cancellation/revocation or list/search operations, but core workflows have no major dead ends.