Read Zillow listing details

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the description focuses on what annotations can't say: exact per-row and per-run pricing, that blocked/missing homes cost nothing, and that max_charge_usd halts the run while still returning summary rows. That is materially useful pre-call context for an agent weighing cost against completeness.

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 the two input modes, followed by return shape and then cost, which is the right order. The pricing sentence is dense and runs three amounts together, but no sentence is 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?

With six optional parameters, no output schema, and a costly open-world read, the description compensates by describing the returned fields, the free-row cases, and the cost model per mode. An agent has enough to choose inputs and predict charges without opening anything else.

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 coverage is 100%, so the baseline is 3; however the description adds economic meaning the schema does not, tying read_details to the 0.006 vs 0.002 per-row price and to gaining description and agent data. It also frames the flat-row output that each parameter type produces.

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 verb (read) and resource (Zillow home details) and enumerates the three lookup modes (URL, ZPID, street address) plus the ZIP-search mode. It also states the return shape: one flat row per home with named fields. There is no sibling to confuse it with, but the scope is unambiguous.

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?

It explains the key operational tradeoff: read_details=false returns cheap search rows, while true reads each home page at the listing price and adds description and agent. It also scopes listing_status to ZIP-code use only and explains the free-row outcome for blocked/missing homes. What's missing is explicit when-not-to-use or prerequisite guidance, but for a single-purpose read tool this covers the decision points.

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