roki_audit_integrationReturn the checklist to audit existing ROKI code, ordered by how badly each item fails in production. Use it when reviewing an integration you did not write, or before going live.
| Name | Required | Description | Default |
|---|---|---|---|
| focus | No | Optional area: "webhooks", "security", "payments", "reversals". |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds the behavioral detail that the checklist is 'ordered by how badly each item fails in production,' which tells the agent about result prioritization. No contradictions.
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 with no filler; the purpose and usage are front-loaded. Every word contributes meaning, and the structure is ideal for quick comprehension.
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?
This is a low-complexity tool with one optional parameter, full schema coverage, and strong annotations covering safety. The description's promise of a checklist is sufficient; no output schema is needed and the context is 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 schema provides a complete description for the only parameter 'focus', including allowed values. The tool description does not mention parameters, but with 100% schema coverage the agent already has the needed information, so a 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?
The description uses a specific verb 'Return' and identifies the resource as 'the checklist to audit existing ROKI code', clearly distinguishing it from sibling tools that provide guides, examples, or operations. The phrase 'audit existing ROKI code' precisely defines the tool's scope.
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?
States explicitly 'Use it when reviewing an integration you did not write, or before going live,' giving clear contextual guidance. It does not mention alternatives or exclusions, but for this simple checklist tool, the likely use cases are fully covered.
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.
Each tool has a clearly distinct purpose, from searching docs to validating requests to verifying webhook signatures. Even similarly named tools like roki_get_integration_example and roki_scaffold_integration are differentiated by 'complete runnable' vs 'skeleton'.
Tools mostly follow a roki_verb_noun pattern (get, list, search, validate, verify), but a few deviate with noun-only names like roki_status and roki_sandbox_info. The prefix and clear verbs make the pattern predictable overall.
18 tools is on the heavy side, but each serves a distinct role in the integration workflow covered by this server. The count is justified given the breadth of documentation, validation, sandbox, and example generation features.
The tool surface covers the full lifecycle of an integration: discovery (search_docs, list_operations), learning (guides, examples, schemas), validation (validate_request), sandbox testing (sandbox_try), verification (verify_webhook_signature), and post-integration auditing. No obvious gaps for the server's stated purpose.