Ask OEX to look again — what a business does after fixing something. Inspects the website if one is supplied. Rate-limited, and a check that could not run is reported as unable-to-verify rather than as fixed.
| Name | Required | Description | Default |
|---|---|---|---|
| checkId | No | Optional: recheck one finding rather than all. | |
| businessId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses two important behaviors: rate-limiting and the 'unable-to-verify' error handling. It also mentions website inspection. This goes beyond a simple 'recheck' and helps an agent anticipate outcomes, though it stops short of describing the full return format or non-error results.
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 succinct sentences. The first sentence front-loads the primary purpose, and the second packs two distinct behavioral notes (website inspection and rate-limited/error reporting) without redundancy. Every word earns its place.
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 tool with no output schema and a two-parameter schema, the description covers the most critical operational detail (the unusual 'unable-to-verify' outcome) and the contextual trigger ('after fixing something'). It does not explain what a successful recheck returns, but given the action-oriented nature and the clarity of the behavior, 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 description coverage is 50% (only checkId is documented in the schema). The description does not add any parameter-specific semantics; it only implies the business context via the phrase 'a business.' This is adequate but not compensatory for the undocumented businessId since the agent can infer its meaning from the tool name and general context.
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 identifies the tool as a re-check action ('Ask OEX to look again') specifically for after a fix, distinguishing it from the initial check (check_business_health) and retrieval (get_business_health). It also states the scope (inspects website if supplied), making the 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 explicitly states the intended use case: after fixing something. This implies a temporal relationship to prior fixes and suggests it should not be used for initial checks. However, it does not explicitly name alternatives or exclusions, so it misses the highest bar.
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.
Several tools are effectively duplicates or near-duplicates: get_emerging_signals is an explicit alias for list_economic_signals, resolve_entity and resolve_entities overlap heavily, and the markdown variants duplicate their non-markdown reports. Pairs like compare_communities/compare_municipalities and search_businesses/search_licensed_businesses also require reading long contracts to avoid misselection.
Tool names overwhelmingly follow a snake_case verb_noun pattern with sensible verbs like get_, list_, search_, and compare_. The main deviations are the backwards-compatible get_emerging_signals alias and prefix choices such as check_business_health vs get_business_health that obscure the underlying distinction.
70 tools is an extreme surface for any MCP server, far beyond the 25+ 'too many' threshold. The set is fragmented by format variants, aliases, and multiple overlapping lookup tools, making selection and maintenance costly.
The domain surface is broad: entity resolution, business health, labour, community economy, procurement, and governance evidence are all covered in depth. However, there are notable lifecycle gaps—no sandbox deletion, consent revocation, health-action cancellation, or actual exchange/connect/apply step—that leave agents with dead ends.
