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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. Beyond that, the description adds real value: it names the source report, explains why vacant units are included (accurate space counts and occupancy rates), states that output is labelled per Location, and warns that an unreachable Location is reported as skipped. That is useful operational context a caller could not get from annotations.

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?

The core purpose is front-loaded and the location rules follow logically with no filler. The parenthetical report reference and the skipped-Location note both earn their place. Minor deduction for the uneven line wrapping and the trailing run-on blank-default sentence, which reads as unedited.

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?

An output schema exists, so return-value shape needn't be explained, and the location-skipping behavior is covered. However, for a tool with four independent scoping parameters and a dense family of sibling analyses, leaving three parameters undocumented and never clarifying the location/portfolio precedence makes the definition only minimally sufficient for a correct invocation.

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 the load, and it only documents one of four parameters (location). It explains the location format, the "all" sentinel, and blank-default behavior well, but portfolio, as_of_date, and property_ids have no meaning attached anywhere — including the interaction between location and portfolio, which is the most likely source of a wrong call.

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 sentence names a specific verb-and-resource pair: occupancy plus scheduled rent summary for a portfolio. Naming the underlying report (SummaryRentRoll, report 69) and noting it includes vacant units makes the scope concrete. It doesn't explicitly differentiate itself from close siblings like analyze_occupancy_trend or analyze_rent_composition, which keeps it at 4 rather than 5.

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?

The description gives strong guidance on how to scope the run by location (single ID, comma list, or "all") and points to list_locations for discovery. But it gives no guidance on when to choose this tool over the many adjacent analysis siblings, and doesn't explain how portfolio, as_of_date, or property_ids combine with location. Usage is implied rather than stated.

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