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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description goes beyond them by disclosing output edge cases: break-even runs is null when the interval does not show a saving, and the user's estimate is omitted where success is not accepted or the baseline falls outside the measured range. It does not mention auth or rate limits, but for a read-only estimator the added result semantics are substantial.

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?

It is front-loaded with the result shape, then cleanly partitioned into 'Use when', 'Not for', 'Input' and 'Output' segments, so every sentence earns its place. The phrasing is densely packed with clauses, which costs a little readability, but there is no 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?

With no output schema, the description carries the return contract and does so well: it names the ak.roi.v1 shape, states one economics entry per measured model, and explains the null break-even and omitted-estimate cases. Combined with the input guidance, an agent has everything needed to call and interpret this 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 description coverage is 100%, so the baseline is 3 and each parameter is already documented. The description still adds relational meaning beyond the schema by pairing expected_runs with baseline_cost_estimate_usd ('an estimate at your scale') and by clarifying that model narrows output to one model while the measured-range constraint governs whether baseline is usable.

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 opening clause states a precise verb and resource ('expected saving per run, break-even runs and net saving over expected_runs, with intervals') and scopes it to 'one capability and no task'. The 'Not for' clause explicitly separates it from evaluate_capability (single task decision) and compare_capabilities (multiple candidates), so an agent can distinguish it from siblings without opening schemas.

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?

It gives explicit 'Use when: you know the capability and want its economics on each model the registry measured' plus a named 'Not for' list with the two competing siblings and the condition that selects each. When-to-use, when-not, and alternatives are all present.

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