create_connectorCreate or update a Klarefi verification connector manifest. The connector is active as soon as this returns — there is no draft/review step, so review its functions before routing live traffic.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While destructiveHint=true is already annotated, the description adds meaningful behavioral context: the connector is active as soon as the call returns and there is no draft/review step. It also warns about the irreversibility of routing live traffic, which goes beyond the raw annotation.
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-loads the purpose, and every clause adds value. It wastes no words and communicates the essential behavior and caution efficiently.
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 description is clear about the tool's core behavior and the critical consequence of immediate activation, which is especially important given destructiveHint=true. It lacks parameter-level details and does not describe potential return values, but the absence of an output schema and the schema's high coverage partially mitigate this. For a mutating tool with a warning, the description 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?
The description does not explain any parameter semantics; it only mentions 'functions' in the context of review. However, schema description coverage is 100%, so the baseline is 3, and the description does not add significant value beyond the schema's parameter names.
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 specific verbs 'Create or update' with a clear resource ('Klarefi verification connector manifest'). It also differentiates from the sibling 'create_connector_from_openapi' by focusing on direct manifest creation/update, and adds unique context about immediate activation.
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 clear context that the connector becomes active immediately and there is no draft/review step, advising the user to review functions before routing live traffic. It does not explicitly name alternatives or state when not to use this tool, but the caution clarifies a key usage consideration.
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.
Most tools have clearly distinct purposes, such as answer_fields vs answer_question or the various intake actions. However, get_case, get_case_package, and get_case_workspace all retrieve case-related information and could be confused, and create_connector vs create_connector_from_openapi are similar. Overall, descriptions help separate them.
All tool names follow a consistent verb_noun pattern in snake_case, such as create_, get_, list_, save_, submit_, upload_, and wait_. The naming is highly predictable and uniform across the set.
With 20 tools, the server is slightly above the typical well-scoped range of 3-15 but still reasonable for a case-management platform covering intake, review, connectors, and workflows. Each tool serves a distinct function, though some consolidation could be possible.
The tool surface covers the main intake, case review, and connector lifecycle well. Minor gaps exist: there is no explicit tool to complete or reopen a case, and workflows cannot be published or activated after saving a draft. These are workable but notable omissions.