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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the output is an advisory plan rather than data, it will explicitly declare 'what the public record cannot answer at all', and it accepts an already_tried input to avoid dead-end re-recommendations. No return format is given, but an output schema exists, so that omission is defensible.

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 core statement, with the usage directive second and examples last, which is the right ordering. The parenthetical source list ('county parcel GIS, Census CBP/ACS/permits, BLS series...') is dense, and the run-on opening sentence is long, but nothing is wasted for a tool whose value is conceptual framing.

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 agent has everything needed: all three parameters are documented at 100% coverage, an output schema handles the return shape, annotations cover the safety profile, and the description supplies the conceptual framing plus worked examples. There is no obvious gap an agent would hit before invoking it.

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 100%, so the baseline is 3 and the schema carries parameter documentation. The description still adds value by showing four concrete example invocations that demonstrate what a well-formed question and place look like, and the schema itself goes further by explaining that state choice determines whether sale prices exist. Modest but real lift over the structured fields.

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 states a specific verb and resource — 'returns a source-first RESEARCH PLAN' — and immediately enumerates what the plan contains (which record settles the question, how to reach it, what it's worth, what it cannot answer). This decisively separates it from data-returning siblings like twin_cities_records or twin_cities_lookup, which fetch records rather than routing to them.

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 gives a clear temporal/contextual trigger: 'Use it before researching a local market, to find the administrative record that settles the question.' That is genuine when-to-use guidance. It stops short of naming alternatives or stating when NOT to use it (e.g. when you already know the dataset and should call twin_cities_datasets directly).

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