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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is the data provenance: results come from a 'retained county assessment snapshot' and report observed counts plus total county-appraised value. That tells the agent the data is a stale snapshot and what it means, well beyond annotations. Missing only details like freshness or pagination behavior.

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?

Two tight sentences, with the identity and scope stated first and the disclaimers second. Every clause carries information, including the legacy-name caveat that prevents misuse.

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?

For a read-only snapshot query with no output schema, the description adequately conveys what comes back (property counts and county-appraised value) and what it does not. It falls short on the four undocumented input parameters, which an agent must guess at from the schema names alone.

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% across four parameters (county, state, limit, format), and the description only obliquely implies county-level scoping via 'county assessment snapshot'. It says nothing about the required state code, the 1-100 limit, or the json/csv format choice, so it does not compensate at all for the undocumented schema.

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 ('inspect named portfolio ownership in a retained county assessment snapshot') and explicitly disclaims the misleading legacy name by ruling out cash purchases, active buyers, acquisition price and buy box. It does not, however, name a sibling to use for actual buyer research, so the routing signal is only half-complete.

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?

The negative framing ('does not establish cash purchases, active buyers...') implicitly tells the agent when this tool is the wrong choice, which is valuable. But there is no positive when-to-use statement and no pointer to an alternative sibling, leaving the agent to infer the correct path.

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