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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value on top by disclosing what is excluded from the estimate (storage, network egress, taxes, idle time) and that prices are listed rates rather than live availability. Those caveats are exactly the kind of assumption an agent needs before presenting a number as a cost.

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 sentences, front-loaded with the output shape and followed by the caveat; nothing is padded. It is dense but each clause carries distinct information, so only the slightly clipped phrasing keeps it from a 5.

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 an output schema present the description need not explain return values, and it covers the material assumptions (what is and isn't counted, listed vs available rates). The only gap is that it says nothing about how the 'median rate card' comparison is selected, but the parameter defaults in the schema largely fill that in.

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%, so the schema fully documents gpu, gpus, hours, limit, market, and region, making 3 the baseline. The description's mention of 'N GPUs', 'a number of hours', and 'the cheapest rate cards' loosely echoes the gpus/hours/limit parameters but adds no syntax or default detail beyond them, and market is not addressed.

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 precise computation: cost of N GPUs of one model for a number of hours, at the cheapest rate cards and the median, with the arithmetic shown. This is clearly a derived-cost tool rather than a raw price lookup, which separates it from gpu_prices. It does not name any sibling explicitly, so it falls short of a 5.

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 defines the tool's scope ('rental fee only', 'listed rates, not availability') but never says when to reach for it instead of gpu_prices, buy_vs_rent, or token_cost. The scope limits are useful but they are boundary definitions, not use-vs-alternative routing.

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