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

Annotations only cover the safety profile (read-only, non-destructive, closed-world), and the description goes well beyond that: it explains that on-demand is list price while spot blends spot, interruptible, and marketplace asking prices, states the two-provider inclusion threshold, and documents the not_found error shape.

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-loaded with the resource and unit, then tiers of detail. Dense but nearly every clause earns its place; the field enumerations are long, though they substitute for the missing output schema.

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?

With no output schema, the description carries return-shape responsibility and does so: it lists the per-class fields for on-demand/spot and for memory tiers, plus the unknown-model error payload. An agent has everything needed to call and parse it.

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 coverage is 100%, so baseline is 3, but the description adds the tier behavior of the empty model value (16, 64, 256, 512 GB) and clarifies that response_format=json returns the object with source numbers and omitted fields stripped.

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 resource and unit up front: the latest GPU rental price index in US dollars per GPU-hour. It is clearly distinct from siblings like market_totals and get_asset, which an agent can tell apart 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?

Gives explicit call conditions tied to the model parameter: omit it for every published model plus memory tiers, pass one name for that model only. It does not, however, name or exclude any sibling tool, so routing against market_totals is left to inference.

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