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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. Beyond that the description adds genuinely useful behavior: the result is an aggregation (cheapest across providers, not a full price table), it is limited to on-demand pricing, and the data is refreshed hourly, which tells the agent how fresh a quote is. It stops short of stating currency, whether the winning provider is returned alongside the price, or what happens for an unknown GPU.

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?

One dense sentence with no filler; the qualifiers that matter (cheapest, on-demand, per GPU-hour) are front-loaded and the provider list and refresh cadence trail as supporting detail. Nothing needs to be cut.

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 one-optional-parameter tool this is close to sufficient, but with no output schema the description should say what a result record looks like — price, currency, provider, GPU model, timestamp — and what is returned when no match exists. As written an agent knows the concept of the output but not its shape.

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% for the single optional 'gpu' parameter, and the schema already explains 'GPU id or name. Omit for every GPU.' The description adds no syntax, accepted aliases, or format guidance beyond that, so this is the baseline case where structured fields do the work.

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 pins down a specific resource with real scope: 'cheapest on-demand price per GPU-hour' — not all prices, not spot/reserved — across a named provider list, refreshed hourly. An agent can tell immediately that this is a price-lookup tool and not a VRAM/model-fit tool like its siblings.

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?

Usage is only implied: the description tells you what data exists, so an agent infers it should call this when it needs a cost figure. There is no explicit when-to-use, no statement about when a sibling (estimate_vram, models_that_fit) is the better choice, and no mention of how to combine this with those tools. The sibling names are unrelated enough that confusion is low, which keeps it above a 2.

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