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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds genuinely new behavioral facts: output is labelled per Location, unreachable Locations are reported as skipped, blank location falls back to all-or-single Location, and the result is a point-in-time snapshot rather than a series.

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?

Front-loaded with what the report is, then what it returns, then the location contract — a sensible order with little filler. Slightly verbose in the metric enumeration, and the trailing location paragraph is dense, but no sentence is wasted.

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?

Output schema exists, so return values need not be explained (though the description does so redundantly). The real gap is input coverage: four of five parameters — notably portfolio/property scoping and as_of_date, which materially change the result — are undocumented for an analytics tool where those axes matter.

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% across five parameters, so the description must carry the burden — yet it only explains `location` (including the 'all' sentinel and blank fallback). `top_n`, `portfolio`, `as_of_date`, and `property_ids` are never mentioned; 'top-N longest-vacant units' only weakly hints at top_n and says nothing about defaults or behavior.

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?

Names the specific resource (vacancy, Rent Manager report 74) and enumerates exactly what the snapshot contains: vacant count, average/oldest days vacant, foregone rent, aging buckets, unit-type breakdown, and top-N units. The line 'Point-in-time snapshot, not a time-series' actively separates it from time-series siblings like analyze_occupancy_trend and analyze_payment_trends.

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?

Usage is implied by the snapshot framing and the location-precedence note, but there is no explicit when-to-use/when-not guidance relative to the many adjacent analyze_* tools (analyze_availability, analyze_rent_roll, make_ready_summary, unit_marketing_status). The agent must infer selection from the output description rather than a stated rule.

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