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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered; the description goes further by disclosing data semantics the schema cannot: prices are 'today as posted,' only offers rentable now are included, Seeweb prices are euro-converted at the ECB rate, SaladCloud coverage begins 2026-11-01, and configurations are not standardized so results are not comparable across GPUs. It does not mention pagination or result-count limits, but an output schema exists to carry the return 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?

The purpose is front-loaded, but the body degenerates into a 30-plus-name provider roll call (RunPod, Vast.ai, ... FriendliAI, Seeweb) that consumes most of the text and delivers little decision value versus a summary like 'major clouds and GPU marketplaces.' The 2026-11-01 SaladCloud footnote is buried inside that list, where it is easy to miss.

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 read-only listing tool with an output schema and a fully described single parameter, the description covers scope, freshness, currency handling, and the key caveat about non-standardized configurations. Missing only operational details such as result volume or pagination behavior, which is minor here.

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% and the single 'gpu' parameter is already documented with examples in the schema. The description's roll call of example models (RTX 5090, A40, L4, V100) echoes the schema example rather than adding new meaning, such as whether matching is exact or fuzzy. Baseline 3 applies.

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 names a specific resource (rental prices of every GPU, lowest and median price per GPU-hour, offers, stock, providers) and explicitly distinguishes itself from the sibling get_gpu_prices by stating that the standardized index GPUs live there and this covers the rest. An agent can tell the two apart without opening either 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?

It states the routing condition clearly: 'Not an index... the GPUs with a price index are in get_gpu_prices,' which tells the agent to use the sibling when standardized cross-configuration comparison is needed. It lacks explicit when-not guidance (e.g., for single-GPU history or specific provider filtering, which other siblings like get_gpu_price_at or get_provider_prices serve).

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