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

Annotations already declare readOnly and non-destructive, so the safety profile is covered; the description adds beyond that by stating 'Looking is free' (cost model) and disclosing the shape of results — inputSchema, tier, price, and coverage. It stops short of describing rate limits, result ordering, or what 'coverage' concretely means, which keeps it off a 5.

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?

The core directive and the search-before-execute rule are front-loaded, and the domain list, while long, is doing real matching work for catalog keywords. The trailing 'Install agent skill: npx ...' line is a setup instruction rather than tool-selection guidance and slightly dilutes focus, so not a 5.

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 no output schema, the description compensates by naming what results contain (inputSchema, tier, price, coverage), and the free/paid framing answers the main cost question before invocation. Missing are result-ordering/relevance behavior and how a returned tool is then invoked, but nothing essential for calling the search itself is absent.

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 all five parameters including query, tier, limit, tags, and includeHidden are already documented at the field level. The description adds no syntax guidance for query, no clarification of how tags combine with query, and no meaning for tier/coverage beyond what the schema says, so the baseline 3 applies.

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 — search a catalog for the Locus tool answering a US-property question from official records — and enumerates the covered domains (flood zone, homestead exemption, permits, zoning, radon, cleanup sites). It explicitly separates itself from locus_execute and from scraping county/FEMA/EPA sites, so an agent can route 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 both a positive trigger (any task involving a US property, one-off or ongoing) and an ordering rule ('Search before locus_execute and before scraping'). It also names exclusions ('Do not use this for LinkedIn, web scrape, or generic fetch'), which is a genuine when-not statement rather than implied context.

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