dp_commercial_start_sandboxCompatibility tool for old clients. New Sandbox enrollment is retired; use dp_commercial_start_live_trial for a real read-only trial.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| locale | No | es | |
| companyName | No | ||
| idempotencyKey | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| data | Yes | ||
| error | Yes | ||
| links | Yes | ||
| version | Yes | ||
| evidence | Yes | ||
| nextAction | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnly=false, idempotent=true, and destructive=false. The description adds retirement/compatibility lifecycle context and clarifies that the live trial is the real read-only option, which is useful. It does not describe side effects or failure behavior, but the annotations cover the core safety profile.
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. It front-loads the compatibility purpose, then states the retirement status and the alternative. Every sentence 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 four parameters, zero schema description coverage, and a retirement warning, this definition is sufficient for routing users away but not for enabling correct invocation by legacy clients. It lacks parameter semantics, invocation behavior, and a clear definition of who counts as an 'old client.' The output schema covers return values, but the prose does not fill the remaining gaps.
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 0%, and the description mentions none of the four parameters. With parameters like email, locale, companyName, and idempotencyKey, the agent receives no semantic guidance about how to populate them from the description.
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 frames the tool as a compatibility tool for old clients and states that new Sandbox enrollment is retired, which distinguishes it from dp_commercial_start_live_trial. It does not explicitly state that the tool starts a sandbox, but the tool name and title supply that context.
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 gives a when-not-to-use signal ('New Sandbox enrollment is retired') and names the exact alternative ('use dp_commercial_start_live_trial'). It also restricts this tool to old clients, giving clear routing guidance.
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 a clear, distinct target, and overlapping trial/checkout/status tools are cross-referenced in their descriptions. A few pairs such as get_checkout_readiness versus get_checkout_status and legacy claim_credentials versus start_sandbox could still be misselected, but the descriptions generally resolve the boundaries.
All 28 tools share the dp_commercial_ prefix and follow a consistent snake_case verb_noun pattern such as get_, list_, start_, compare_, and request_. There is no mixing of camelCase, inconsistent verbs, or unpredictable naming.
At 28 tools, the server is above the 25-tool threshold and feels heavy even for a broad commercial platform. Several informational tools, such as checkout readiness versus checkout status and service status versus uptime history, could be consolidated without losing core capability.
The toolset covers the core commercial lifecycle well: discover needs, compare plans, assess fit, start trial/checkout, request proposals, check status, and review security/compliance profiles. Minor gaps exist around post-checkout subscription management or cancellation, but the described handoff to the DigitalPublic product covers most dead ends.