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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description's job is to add context beyond that. It does: it discloses the snapshot-vs-time-series nature of the result and the composition of the payload (aging buckets, unit-type breakdown), which tells the agent what it will actually get. It stops short of noting rate limits, pagination, or scoping behavior for portfolio/property filters.

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 short sentences, each carrying distinct information: identity, metric list, payload composition, and the temporal caveat. It is front-loaded with the core purpose and has no filler.

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 values need not be documented, yet the description still usefully previews them. The tool's scope and data shape are clear; the only real gap is that none of the four inputs (especially as_of_date and the portfolio/property filters) are described, which matters for 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% across four parameters, so the description must compensate and largely does not. 'Top-N longest-vacant units' loosely maps to top_n and 'per property' loosely hints at property_ids/portfolio, but as_of_date and the semantics of the filter strings are never explained.

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 names a specific analysis ('Vacancy snapshot per property') and enumerates the exact outputs: vacant count, average/oldest days-vacant, foregone monthly rent, aging histogram, unit-type breakdown, and top-N longest-vacant units. It also cites the underlying report (74), and the 'point-in-time snapshot, not a time-series' line distinguishes it from trend-oriented siblings such as analyze_occupancy_trend.

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 rather than stated: an agent can infer this is the tool for vacancy-level analysis, and the 'not a time-series' note implicitly points to trend tools for temporal questions. However, no sibling is named and there are no explicit when-to-use/when-not conditions, so the routing burden falls on the reader.

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