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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds important behavioral context beyond annotations: it discloses that the dataset is a demo covering only Montgomery County, TX, that sample properties only are included, and that broader county coverage must be confirmed before purchase. This is valuable, non-obvious information that shapes agent expectations.

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 longer than average but every sentence contributes: the core lookup purpose, returned fields, example questions, exclusions, and the demo coverage limitation. It is front-loaded with the main purpose and avoids vague filler, though the support email sentence is slightly tangential to agent invocation.

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?

There is no output schema, so the description appropriately enumerates the returned fields and clearly states what is not returned, covering agent expectations well. It also communicates the coverage limitation and required confirmation for broader use. Missing details like response format or error behavior are minor gaps for a simple read-only lookup 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?

The input schema has 100% description coverage for both parameters, so the description does not need to add much here. It does restate that queries can be street addresses or account numbers, but that is already in the schema, and no additional syntax, format, or county behavior details are provided beyond the schema 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 clearly states the tool looks up real estate property data by street address or account number and lists the exact fields returned, which makes the purpose immediately understandable. It does not explicitly name sibling tools like property_search_owner or property_value_history to draw a contrast, so it falls short of a 5, but the scope is specific enough to distinguish the primary use case.

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 description gives explicit example questions and says to use the tool for real estate lookups, which provides clear context on when to invoke it. It also notes that owner names, heirs, deed opinions, and title conclusions are not returned, which is a useful exclusion, but it does not name alternative tools that should be used for those needs.

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