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

Annotations already declare this a safe, idempotent, non-destructive read, and the description still earns its place by disclosing the pricing schedule (1 credit base, per-section costs, terrain at 2), the partial-failure contract that an unavailable section refunds its credits, and the deliberate exclusion of owner data. Those are operational facts an agent cannot get from the annotations or schema.

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?

One dense paragraph that front-loads the purpose, then sections, then the id contract, then costs, then the owner-data exclusion — a sensible ordering with little filler. It is long and could be split into short blocks for scanability, and the per-section credit list is somewhat repetitive of the section list itself.

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 shape needn't be explained, and the description still covers what an agent needs: the id-to-get_record handoff, partial section availability with refunds, the cost of each optional section, and where the excluded owner fields live instead. Nothing required to invoke it correctly is missing.

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 largely does: it glosses each section value (utilities as water/sewer service areas and treatment plants, environment as flood/wetland coverage and nearby sites, terrain as the first parcel's elevation and slope) and explains that address and longitude/latitude are alternative ways to fix the location. It omits the coordinate bounds (-85 to 85 latitude, -180 to 180 longitude), the maxLength/maxItems limits, and whether both address and coordinates may be supplied together.

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 and resource with its scope bounded: find parcels at one US location, either an exact address or WGS84 longitude/latitude. It also names what the tool is not (owner names/mailing addresses never returned here) and points at the tool that opens each returned id, so an agent can separate it from get_record and enrich without opening a schema.

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 usage context: use it for a single US location, optionally attaching context sections, and it explicitly routes owner-name needs to the paid owner field group of the batch parcel-fields tool at 2x credits. It stops short of stating precedence between address and coordinates or when to prefer enrich or ask over plain lookup, so one inference step remains.

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