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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds genuine context beyond that: deterministic behavior, the formula version to cite (calc.compare_proposals@1), the presence of returned steps, and the instruction to surface warnings. It does not describe failure behavior (e.g., what happens with fewer than 2 proposals or an invalid schedule), so it adds value but not rich behavioral context.

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?

Two tightly packed sentences: the operation and output basis come first, followed by the determinism/citation protocol. Both sentences earn their place, though the second is a dense clause chain that could be split for readability.

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?

No output schema exists, and the description partly compensates by naming the two result concepts and pointing to 'returned steps' and 'warnings', so an agent knows roughly what comes back. Combined with 100% parameter coverage and strong annotations, the definition is nearly complete; a brief note on output ordering or error conditions would close the remaining gap.

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 100% schema description coverage, the baseline is 3, and the description exceeds it by explaining what the `perspective` enum actually computes — effective occupancy cost for tenant vs. discounted net effective rent for landlord — plus the fact that all proposals are ranked on one shared discounted basis. That is semantics the schema does not supply. It says nothing additional about `discount_rate_annual`, so it is not a 5.

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 gives a specific verb ('Rank') and resource ('2–20 lease proposals') and states the output basis (discounted $/SF/yr, effective occupancy cost vs. discounted net effective rent). The 2–20 cardinality implicitly separates it from single-proposal siblings like calc_net_effective_rent, but no sibling is named, so differentiation still requires inference.

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?

'Use this instead of doing the math yourself' is a clear directive against the manual-math alternative and 'Deterministic' reinforces why. However, there is no explicit when-not guidance and no routing to/away from the many calc_* siblings (calc_net_effective_rent, calc_rent_schedule, calc_renew_vs_relocate), which is a real gap in a crowded calc namespace.

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