USAC, the one-token dollar. Mint, hold, get more USAC as the pot earns (live Kamino + optional trade sleeve). Redeem at NAV. POST action=mint with usd. Talon never signs. Not issued by the United States. Not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| usd | No | Dollars to mint | |
| risk | No | conservative | |
| usac | No | USAC to redeem | |
| owner | No | Your id. Defaults to your agent key or guest. | |
| action | No | view | |
| pnlUsd | No | Hands only. Real trade-sleeve PnL to mark. |
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?
With no annotations, the description carries the full behavioral disclosure burden. It adds meaningful traits: yield is earned via 'live Kamino + optional trade sleeve,' redemptions occur at NAV, and critically, 'Talon never signs.' It also includes disclaimers about issuance and financial advice. It could explain custody or side effects further, but it does substantial work beyond the schema.
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 compact and front-loaded: concept, actions, concrete usage, trust signal, then disclaimers. Nearly every sentence adds useful context. The legal disclaimers are boilerplate but not harmful. It earns a high score for efficiency.
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?
There is no output schema, and the description covers only the mint/redeem/hold flows. It omits the 'view' and 'mark' actions, does not explain risk parameter semantics, and says nothing about expected return values or owner default behavior. For a tool with 6 parameters and multiple enum actions, this is incomplete for agents needing to use non-default flows.
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 adds meaning beyond the schema by connecting action=mint with usd and redemption with NAV. However, it does not clarify the semantics of the risk enum or the 'mark' action / pnlUsd relationship, leaving parts of the schema's gaps unaddressed. The schema already documents usd, usac, owner, and pnlUsd, so the added value is moderate.
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 identifies USAC as the resource and states the core verbs: mint, hold, and redeem. The concrete instruction 'POST action=mint with usd' makes the purpose and primary call pattern unambiguous. It does not explicitly distinguish itself from sibling tools, but the resource and actions are specific enough to avoid confusion.
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?
It gives clear usage context: mint by supplying USD, hold to earn yield, and redeem at NAV. It also provides a concrete invocation pattern. However, it does not explicitly mention when not to use the tool or compare it with the many sibling tools, so it misses the top score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.