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

With annotations already declaring readOnlyHint, idempotentHint, and destructiveHint false, the description adds genuine behavioral detail: 'returns what changed instead' when changed_since is used, 'Not predictions', and the important caveat that proposed owners and percentages are not returned as fact. No contradiction with annotations.

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 description is a single dense paragraph that leads with the core purpose and states, then enumerates the output fields and caveats. Every clause carries meaning, but the long enumeration makes it slightly less scannable than a more structured list; still compact with no 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?

The tool has no output schema, so the description carries the burden of return format and it does so well: fields, record classes, state stages, and source. It also tells the agent what is not returned. The gaps are semantic explanations for the 'view' enum and the 'limit' parameter, which are either self-evident or and supplied by schema defaults. Overall it is complete for a niche search tool.

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 covers tag, query, and changed_since with descriptions, while view and state have enums without descriptive text. The description enriches changed_since by explaining the return-mode shift and lists the states, but it does not explain the 'view' enum (what 'effective' vs 'withdrawn' means) or limit behavior. Given 50% schema coverage this partial compensation lands at a 3.

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+resource: it returns official state records of pending skilled nursing facility ownership changes before they take effect. It names the states, enumerates the return fields (facility, CCN, beds, operators, record class, dates, evidence tags), and explicitly disclaims predictions, clearly distinguishing it from any generic search tool.

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?

Clear context is given: use it for official pending ownership-change records in Kentucky, New York, Rhode Island, New Jersey, and Maine. The 'With changed_since...' clause explains a different invocation mode, and 'Not predictions' sets expectations. However, no sibling is explicitly called out as an alternative and no 'when-not-to-use' guidance is given, which prevents a 5.

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