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

Annotations already cover readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the cost detail (0.10 USDC per call), which is a valuable operational note beyond the annotations, but it does not disclose return format, pagination, or other behaviors. With annotations handling safety, this is adequate but not rich.

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 sentence, front-loaded with the cost warning, followed by a compact but precise description of the returned data. No filler or redundancy.

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 the full burden of explaining what is returned. It covers the range of data (GPU models × providers × markets) and the metrics (lowest/median prices, hyperscaler spots). Minor ambiguity around 'hyperscaler spot per region' could be clearer, but it is sufficient for a snapshot endpoint.

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 tool takes zero parameters, so the schema (empty object) covers everything. The description correctly focuses on the output content rather than parameters. Since there are no parameters, the baseline is 4, and the description adds no parameter-specific semantics because none are needed.

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 states exactly what the tool returns: for every GPU model × provider × market, the lowest and median USD per GPU-hour in the latest snapshot, plus hyperscaler spot per region. It uses a specific verb-resource pattern and differentiates from sibling snapshot tools (ondemand_snapshot, reserved_snapshot, spot_snapshot) by being the general GPU market snapshot.

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?

The description implies when to use the tool (when you need a whole-market GPU price snapshot), but it does not explicitly contrast with siblings or state when not to use it. No alternatives are mentioned, leaving an agent to infer the right choice among the many snapshot endpoints.

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