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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true), so the bar is lower. The description adds the data source (federal HMDA register) and the coverage window (2018-2025), which is useful context. It does not disclose aggregation semantics, dollar-volume meaning, or whether the data is lagged, but the annotations do most of the behavioral work.

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?

Three sentences, front-loaded with the core question (mortgage lending in a place with dollar volume) before the breakdown rationale and coverage window. Slight redundancy between sentence one and two, but no fluff.

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 analytical query with full schema coverage and no output schema, the description covers resource, scope, source, time window, and the fair-lending framing the tool enables. It lacks explicit sibling routing and return-shape hints, but nothing essential for correct invocation 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 100%, so the schema documents every parameter (year range, county FIPS format, action enum, breakdown enum, two-letter state). The description adds little beyond mentioning the dimension names, so the baseline 3 is appropriate where the schema carries the load.

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States a specific verb+resource: mortgage application outcomes (originated/denied/withdrawn) by county/state/year from the federal HMDA register. This is distinguishable from siblings like hmda_lender_activity (lender-centric) and hmda_loan_records (record-level). The identity is clear, but the description does not explicitly differentiate itself from those HMDA siblings.

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 implies the fair-lending use case (breaking down by race/ethnicity to see differential outcomes) and supplies the required inputs (place + year). However, it never states when to use this tool versus hmda_lender_activity or hmda_loan_records, nor does it spell out that a county OR state is needed. Usage is implied rather than stated.

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