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

With no annotations, the description carries the full burden and does so well: it discloses that results are a historical observation from the public CFPB HMDA 2025 record, specifies the filtering actions and loan type, and warns it is not a prediction about any individual application. This gives the agent important interpretive context beyond the schema.

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 well-organized with clear labels (ANSWERS, PARAM, NOT FOR) and front-loads the most important information. Every sentence adds value: scope, parameter format, output, exclusions, data source, and attribution, 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?

Given a single required parameter, no output schema, and no annotations, the description covers everything needed: what it returns (state 2025 rate and counts against the national 22.1 percent), how input must be formatted, what it excludes, and the data provenance. Nothing essential is missing.

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%, so the description must explain the state parameter, and it does: only two-letter USPS codes like OH or TX are accepted, and full state names are rejected. This is exactly the semantic guidance the agent needs beyond the bare string field.

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 the tool answers specific state-level FHA denial rate questions and explicitly contrasts it with get_metro_lender_gap for metro/city questions, making its scope unmistakable. It names not only the verb/resource but the exact supported query patterns.

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 input constraints (two-letter USPS code only, full names rejected) and clear when-not-to-use guidance with a named alternative for metro/city queries. It also excludes lender-level questions, telling the agent what this tool is not for.

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