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

Annotations already cover read-only, idempotent, open-world, non-destructive semantics, and the description adds genuinely new behavior: it caps the row count and reports truncation, and warns that a large county returns tens of thousands of rows. It does not detail pagination or auth requirements, but the truncation disclosure is valuable context beyond the 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?

Three sentences, front-loaded with the resource identity before usage and behavior. Dense and mostly waste-free, though the field enumeration is slightly listy and could be trimmed.

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?

With no output schema, the description usefully covers the return shape (loan-level rows with named fields) and the truncation behavior. It leaves some gaps around default behavior when no geography filter is supplied, but for a read-only filtered-list tool it is largely complete.

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 already documents every parameter including the enum-like action values and the county/state either-or rule. The description only restates 'filtered by geography and outcome', adding no syntax or format detail beyond the schema, so baseline 3 is correct.

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 resource (individual HMDA mortgage application loan-level rows) and explicitly positions it as 'the loan-level rows behind the totals', which distinguishes it from the aggregate siblings hmda_geography_activity and hmda_lender_activity. It even enumerates the returned fields (loan amount, action taken, rate spread, income, LEI, census tract).

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?

Gives a clear selection condition: 'Use when an aggregate is not enough and the individual applications matter.' That routes the agent away from the aggregate tools, though it doesn't name a specific sibling or state when-not to use it beyond that single condition.

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