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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the aggregation methodology (median of each provider's cheapest offer, per GPU-hour, USD), which determines how the numbers should be interpreted. With the annotations plus an output schema, a 3 reflects that safety and return shape are already handled elsewhere.

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?

Two tight sentences with no wasted words, and the core definition plus methodology are front-loaded before the parameter bound. The terse phrasing and mid-description line break make it slightly harder to scan, but nothing is superfluous.

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?

An output schema exists, so the description needn't explain return values, and the aggregation methodology makes the numbers interpretable. The notable gap is `pricing_type`, an undocumented parameter with no enum, which is a meaningful omission for a three-parameter tool with zero schema description coverage. Handling of missing days or partial provider coverage is also unaddressed.

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 0%, so the description must carry the burden. It documents the `days` range (1-90) beyond the schema's bare default of 30 and implies `gpu` accepts one GPU family. However, `pricing_type` is never mentioned at all — no valid values, no meaning of the 'on_demand' default, and there is no enum in the schema, so the agent is left guessing about that parameter entirely.

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 ('Daily price history for one GPU family') and even specifies the aggregation method: each day's median across providers of each provider's cheapest offer in USD per GPU-hour. That is far more precise than the title. It stops short of differentiating itself from the sibling gpu_price_forecast, so an agent must infer that this returns historical data while the sibling projects forward.

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?

There is no explicit when-to-use guidance and no mention of alternatives. It never says to use this for historical trends versus gpu_price_forecast for projections, or cheapest_gpu for current spot pricing. The only usage constraint given is the 'days: 1-90' bound, which is a parameter limit rather than routing guidance.

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