get_llm_unit_economics

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

No annotations are provided, so the description carries the full burden. It discloses that if metric_count is omitted, the tool returns total spend only and asks for the count. This is a useful behavioral trait. However, it does not mention whether the tool is read-only, requires authentication, or has any side effects. The mutation safety profile is unclear.

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 is well-structured with a brief purpose statement, a summary of the calculation, and then enumerated arguments and examples. It is concise and front-loaded. Minor redundancy could be trimmed (e.g., the division line repeats the purpose), but overall it is efficient.

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?

Given no output schema, the description should explain the return value. It mentions cost-per-X but does not specify the format (e.g., numeric value, currency, precision) or whether the result includes total spend. The omission of metric_count leads to an intermediate response, but the description does not elaborate on what that response looks like. More details on the output would improve completeness.

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 coverage is 0%, so the description must add meaning beyond the schema. It explains metric_name, metric_count, and days with defaults and context. The examples show typical usage and clarify the purpose of each parameter. This adds significant value, though more details on accepted values for metric_name (e.g., beyond the listed examples) would be helpful.

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 purpose: calculating cost per unit of business value from AI APIs. It specifies the verb 'calculate' and the resource 'cost per unit of business value from AI APIs', and distinguishes from similar tools by focusing on LLM spend. However, it does not explicitly differentiate from sibling tools like get_unit_economics or get_llm_unit_economics_full, which could cause confusion.

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 provides a clear explanation of what the tool does and includes examples that imply usage scenarios (e.g., cost per request, cost per user). However, it lacks explicit guidance on when not to use it or alternatives. For instance, it does not mention that for non-LLM unit economics, one should use get_unit_economics instead.

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