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

No annotations are provided, so the description must carry the transparency burden. It adds context that 'cache writes included' and mentions 'per-model savings', but it does not disclose calculation assumptions, output format, or any limitations. For a calculator, some behavioral context is missing, so it's only partially transparent.

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 description starts by repeating the title, which wastes an opportunity, but then provides a single, information-dense sentence covering inputs and outputs. Overall, it's compact and readable, though the redundancy is a minor flaw.

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 calculator with no output schema and no annotations, the description explains the main inputs and purpose but leaves the return format and detailed output structure unspecified. It's adequate for a simple estimate tool, but an agent may not know what result to expect.

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 compensate. It references monthly input tokens, cacheable share, and hit rate, mapping to three of four parameters, but does not clarify that monthlyInputTokensM is in millions or that percentages range 0-100, and modelId is unmentioned. It provides some semantic context but not complete compensation.

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 clearly states the tool estimates how much prompt caching reduces LLM API costs, listing the key inputs (monthly input tokens, cacheable share, hit rate) and mentioning 'per-model savings, cache writes included.' This distinguishes it from sibling tools like llm_api_cost_calculator by focusing specifically on prompt caching savings.

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 the use case (estimating prompt caching savings) but does not explicitly mention when to choose this tool over alternatives like llm_api_cost_calculator, nor does it state exclusions. It relies on the name and context to convey when it applies.

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