calculate_unit_cost

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

With no annotations supplied, the description carries the disclosure burden and does well: it declares the operation is local and non-transmitting ('nothing is sent anywhere'), names the required input format (FOCUS 1.x CSV, .csv or .csv.gz), and explains the two outputs (cost per unit by month, spend-vs-business growth direction). It does not state error behavior when the supplied months do not overlap the bill, nor whether the source file is left untouched, which keeps it from a 5.

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?

Three sentences, front-loaded with what is computed and on what data, followed by the outputs and then the usage triggers. The privacy aside and the 'Ask the user for the monthly volumes' instruction both earn their place; only the first sentence is on the long side, packing privacy, format, and computation into one clause chain.

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?

There is no output schema, and the description properly compensates by describing both return dimensions: cost per unit by month and whether spend outpaces business growth. Combined with the local-computation notice, the required-input prompt, and the optional tag scoping, an agent has everything needed to invoke it correctly for a 5-parameter, 2-required tool.

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 coverage is 80%, so the schema already documents most parameters and the 3 baseline applies. The description adds useful framing for the units array (business volumes the user supplies), unit_name ('cost per unit'), and the tag pair as scoping to 'one product or team,' but tag_value itself has no schema description and the description only implies it must accompany tag_key.

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: divides monthly recurring spend by user-supplied business volumes to produce cost per unit per month plus a scaling verdict. The phrase 'on the user's actual bill (a local FOCUS 1.x CSV export)' distinguishes it from sibling tools like analyze_bill, forecast_spend, and analyze_cost_allocation, which do not compute unit economics.

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?

Gives explicit trigger phrases ('cost per customer', 'are we scaling efficiently') and a prerequisite instruction to 'Ask the user for the monthly volumes,' which is genuinely actionable. It does not name which sibling to use instead when the agent lacks volume data or wants a different cut of the bill, so it falls short of full when/when-not guidance.

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