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

The description discloses useful calculation behavior: prompt caching up to 90%, batch discounts, and cost comparison across named models. However, with no annotations, it carries the full burden and does not state whether it is purely read-only, what output shape it returns, or what pricing data and assumptions it relies on.

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, front-loaded with the action and object, and every phrase adds specific detail such as discount rates and model coverage without repetition or filler.

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 four-parameter calculator with no required inputs and a fully described schema, the description is nearly complete: it specifies the computation domain, applicable discounts, and model coverage. The only notable gap is the absence of an explicit output description, but the phrase 'cost disparity' conveys the comparison intent.

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 schema already describes all four parameters, so the baseline is 3. The description adds value by tying parameters to caching discounts and batch discounts, and by naming the model set the cost disparity calculation covers, which contextualizes promptTokens, completionTokens, cacheHitRatio, and isBatch.

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?

Description opens with the verb 'Calculate' and a specific resource: multi-model LLM API token inference costs. It further enumerates caching discounts, batch discounts, and the exact model set, making it clearly distinguishable from siblings like cloud_egress_finops.

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?

No guidance is given for when to prefer this tool over alternatives, and no prerequisites or when-not-to-use conditions are stated. The intended use case of comparing LLM token costs across models is only inferred from the name and terms like 'arbitrage'; there is no explicit trigger or context.

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