Rent a GPU (spends balance)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far exceeds the annotations: hard-cap guarantee that the rental is never charged above budget_micro, metering only starting once the machine is verified ready, retry safety via idempotency_key, and the explicit fact that the tool spends money and is refused unless the server started with AMPLERUN_MCP_ALLOW_SPEND=1. The destructiveHint=true annotation is corroborated rather than merely repeated.

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?

Dense and front-loaded: purpose first, then cost/idempotency behavior, then the spend gate. It is longer than strictly necessary (the return-field enumeration partly duplicates its own later statements) but every sentence carries real information.

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 write tool with no output schema, the description covers the return shape (rental_id, state, quote, fee_split, idempotency_key), the cost model, the idempotency contract, the auth prerequisite, and the follow-up sibling. An agent has everything needed to call it 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?

Schema description coverage is 100%, so the schema already documents all seven parameters including budget_micro's cap semantics and idempotency_key's retry behavior; the description largely restates these. Baseline 3 is appropriate since the description adds little parameter detail beyond what the schema carries.

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 ('Rent a GPU'), and further pins the semantics: quotes the template on the offer AND reserves the machine in one step. This distinguishes it from the sibling get_quote (quote only) and get_rental (observe only).

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?

Implicitly contrasts the one-step quote+reserve with the quote-only sibling and points to get_rental for state, and it explicitly states the spend gating condition (AMPLERUN_MCP_ALLOW_SPEND=1). It does not literally say 'use get_quote first if you only want a preview', so it stops short of a full when/when-not routing statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.