Record that this organization is switching from a rival. Once per organization, before its first top-up. Credit added within 30 days of signing up is matched, up to $1,000 in total, as each payment settles (a referral, which matches the same payments, applies instead, never both). Call it once the project's real job runs on Runtime: it records the move, it does not make it.
| Name | Required | Description | Default |
|---|---|---|---|
| provider | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / provider / enumPrevious value: -[
- "e2b",
- "daytona",
- "vercel",
- "modal",
- "cloudflare",
- "fly"
-]New value: +[
+ "e2b",
+ "daytona",
+ "vercel",
+ "modal",
+ "cloudflare",
+ "fly",
+ "blaxel"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish write, idempotent, non-destructive semantics, but the description adds the business consequences: the 30-day window, the $1,000 cap, per-settlement matching, and the referral exclusivity rule. The 'records the move, does not make it' line guards against the misconception that this performs the migration. It does not discuss auth or failure behavior, keeping it just short of a 5.
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?
Front-loads the action and the key constraint, then adds rules and a closing scope clarification. It is dense but several clauses (matching mechanics, cap, referral overlap) serve the business outcome more than correct invocation, leaving some trimmable weight.
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?
No output schema exists, and the description does not indicate what is returned, though for a one-shot recording tool the timing, exclusivity, and effect details cover the practical decision. The one gap is that parameter meaning must be inferred rather than stated.
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% for the single required 'provider' enum parameter. The description implies its meaning ('switching from a rival'), so the agent can infer provider = the rival being left, but it never names the parameter or explains the enum values, which is the minimum needed when the schema provides no prose.
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?
States a specific verb and resource: 'Record that this organization is switching from a rival,' and then sharply bounds the scope with 'it records the move, it does not make it.' No sibling in this large runtime_* set does anything comparable, so an agent can identify the tool's unique job immediately.
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?
Gives explicit timing conditions: 'Once per organization, before its first top-up' and 'Call it once the project's real job runs on Runtime.' It also names the mutually exclusive alternative ('a referral ... applies instead, never both'), which is exactly the when-not-to-use guidance most definitions omit.
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.