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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), so the bar is lower; the description adds genuine behavioral context beyond them — partial-input semantics yielding n/a, and a canonical external reference for identical math. It stops short of stating output shape, rounding, or unit expectations.

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 tight sentences, front-loaded with the metric list, then the partial-input rule, then the provenance link. Nothing is padded, though the external URL is the least load-bearing element for an agent.

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 14-parameter tool with zero required fields and no output schema, the description usefully explains that outputs degrade to n/a and that benchmarks accompany each metric. It never states the return format explicitly, which is the remaining gap given no output schema exists.

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% and each of the 14 parameters is already annotated with its unit and the metric it feeds, so the description adds little. Its only extra is framing that all values come 'from the numbers you give'; baseline 3 applies when the schema does the heavy lifting.

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?

Names a specific verb ('computes') and enumerates the exact metrics produced (Rule of 40, NRR, GRR, magic number, CAC payback, spend per new customer), which is a distinct scope from every sibling calculator (burn multiple, SAFE dilution, term sheet waterfall, etc.). An agent can route to this tool without opening the schema.

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 clear operating context: 'Leave a group of inputs out to get n/a for the metrics that need it' tells the agent partial input is legal and how missing data is handled. It does not name when-not-to-use or point to an alternative sibling, but the metric list itself is the selection criterion.

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