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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: distances are approximate straight-line between public locality centers rather than home locations or driving times, only published homes are returned, and there are no live rates or availability.

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?

Five short sentences, each load-bearing: the core purpose first, then the distance caveat, then the area-key discipline, then the data-availability limit, then the display instruction. No filler or restated schema.

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 no explanation, and the description still adds the render-as-cards instruction and the two most likely failure modes (invented keys, misread distances). Nothing material is missing for a 10-param search tool.

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 only 50% schema description coverage, the description must carry weight, and it does for the most error-prone inputs: the nearArea key must be exact and never invented, and the distance semantics for radiusKm are spelled out. It does not address page, locale, minBathrooms, or how the feature enum relates to amenities, so the compensation is partial.

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 verb (find), resource (published homes), and a precise scoping mechanism (near an exact get_stay_areas key), plus the filter dimensions. This near-area framing implicitly distinguishes it from the sibling search_properties, which is not anchored to a stay-area key.

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?

Gives clear procedural guidance: derive the area from destination evidence or ask the traveler, and never invent a key; also tells the agent to render results as cards. It stops short of explicitly naming search_properties as the alternative when an area key is unavailable, so the when-not is only implied.

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