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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: the default reporting basis follows the organization's saved fiscal calendar (4-4-5, 4-5-4, monthly) while calendar basis uses contractual source periods, and that missing evidence renders as 'unknown' rather than a zero. Pagination behavior and result shape are not described, but with annotations plus a strong data-semantics disclosure this is above baseline.

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 comparison purpose, then basis semantics, then the data-quality caveat. No filler, though 'Missing evidence is unknown' is terse to the point of being slightly cryptic about what renders as 'unknown' in the response.

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 4-param dashboard with no output schema and no annotation detail beyond safety hints, the description covers what is compared and how the two calendar modes work. It leaves gaps on leaseId scoping, year semantics, and pagination, which matter for correct invocation since all parameters are optional.

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 0%, so the description must carry all 4 parameters, and it only explains `basis` (partially — it clarifies what each enum value means, which the enum alone does not). The `leaseId` scope, `year`, and `page` are never mentioned, leaving an agent unable to know whether this tool is org-wide or lease-scoped, or that results are paginated.

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 comparison operation and names the concrete data series being compared (sales forecasts, actual sales, supplemental obligations, posted amounts), which is far more than the tautological title 'Review supplemental rent'. However, it never distinguishes itself from siblings such as get_supplemental_rent_portfolio or the many get_leases_by_leaseId_supplemental_rent_* endpoints, so an agent cannot route on the description alone.

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?

Explains how the two basis modes differ but gives no when-to-use guidance, no exclusions, and no pointer to alternative tools. An agent knows what the basis switch means but not when this dashboard is the correct choice versus the portfolio-level supplemental rent tool.

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