Return a copy-pasteable recipe to VERIFY an integration works: first-call (code↔design, an audit row, correct attribution) or per-user-isolation (a multi-user/broker server runs two users under different credentials and rejects cross-user access). Guidance only — you run the commands.
| Name | Required | Description | Default |
|---|---|---|---|
| scenario | Yes | first-call | per-user-isolation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. The explicit statement 'Guidance only — you run the commands' clearly discloses that the tool does not execute anything and only returns guidance. It also states the output type ('copy-pasteable recipe'), making the tool's behavior transparent.
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 with no filler. The action and resource are front-loaded, each scenario is defined inline, and the second sentence adds a critical clarification about the tool's non-executing nature. Every part 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 simple one-parameter tool with no output schema, the description covers what it returns (copy-pasteable recipe), how the parameter selects behavior (two scenarios), and what it will not do (run commands). An agent has all necessary information to select and invoke this tool correctly.
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 tool description adds substantial meaning beyond the input schema: it explains that `first-call` verifies code↔design mapping, an audit row, and attribution, while `per-user-isolation` verifies two users under different credentials and cross-user rejection. The schema only lists the enum values, so this is genuine added value for choosing the right scenario.
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 and resource: 'Return a copy-pasteable recipe to VERIFY an integration works.' It also enumerates the two distinct verification scenarios, making it unmistakably different from sibling documentation/list tools. An agent can identify this as the verification-recipe tool without opening the schema.
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 gives clear context for when to use it: when you need to verify an integration, with two named scenarios covering common verification needs. However, it does not explicitly contrast with sibling tools like troubleshoot or get_started, nor does it state when not to use it.
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 target clearly distinct concerns: docs, provider operations, SDK wiring, policies, troubleshooting, and verification. However, get_started with no arguments overlaps with list_phases, and fetch_doc/list_skills both provide guidance content, creating minor ambiguity.
The set mostly follows a verb_noun pattern: fetch_doc, list_operations, list_providers, verify_integration, troubleshoot. A few names like policy_language, sdk_integration, and sdk_pattern are noun-led, which is a small consistency break but still predictable and readable.
Thirteen tools is well within the ideal range for a focused onboarding server. Each tool contributes to a different part of the onboarding workflow, and none feel redundant or like filler.
The server covers the full onboarding journey: docs, lifecycle phases, step-by-step flows, provider API discovery, schema retrieval, SDK integration, SDK patterns, policy grammar, troubleshooting, and verification. There are no obvious dead ends or major missing operations for its stated purpose.
