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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior beyond them: outputs are buyer-minus-renter net worth at year 30 after selling costs, interpolated crossover only exists for single-parameter sweeps, and the grid is capped at 50 steps per axis / 400 total grid points. It also discloses the fallback semantics ('other inputs come from base or the site defaults'), which the schema does not state.

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?

Four sentences, front-loaded with what the tool computes before stating input requirements and then use cases. The opening sentence is dense with output enumeration that partly duplicates the output schema, but nothing is filler and the ordering follows what an agent needs first.

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 nested-object, two-axis sweep tool with an output schema and full safety annotations, the description supplies the missing glue: fallback defaults, grid limits, the values-vs-min/max mode, and the single-axis-only crossover. An agent has everything needed to invoke it correctly; return-value description is redundant given the output schema but harmless.

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?

With 75% schema coverage the baseline is 3, and the description earns above that by stating the either/or input mode ('give values[] or min, max and steps') and the 400-grid-point ceiling — relationships absent from the schema, which only bounds individual fields. It does not explain units or the parameter enum semantics, but those are already documented in the schema.

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?

Opens with a precise verb and scope — 'Varies one input (or a grid of two) across a range' — and enumerates exactly what it returns (net worth at year 30 after selling costs, winner, break-even year, crossover). The 'sensitivity questions such as ...' framing makes it clear this is not the single-scenario tool, so an agent can tell it apart from rentbuy_run_scenario and rentbuy_compare_scenarios without opening a 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 explicit context with two concrete motivating questions ('at what rent does buying win?', 'how does the result change with the mortgage rate?'), which effectively routes the agent here rather than to run_scenario. It stops short of naming alternatives or stating when NOT to use it (e.g., for one-off single-point answers), so it is clear but not complete routing guidance.

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