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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds the important non-obvious trait that results carry monthly HUD snapshot provenance, which tells the agent the data is a periodic point-in-time snapshot. It also forecloses inference-style interpretations of the output.

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 tight sentences: capability and grouping first, return payload second, exclusions last. No filler and nothing buried after the exclusions.

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 compensates by enumerating the returned fields (mortgage count, UPB, units, snapshot provenance) and bounding the interpretive claims. Pagination and limit behavior are left entirely to the schema, which is acceptable but slightly under-explained for a tool capped at 100 rows.

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 coverage is 100% and every parameter is self-documented, so the schema carries the burden. The description adds a little conceptual mapping for group_by ('by holder, state, or maturity month') and the exact date-window requirement, but it calls the dimension 'holder' while the enum value is 'lender', a small mismatch that adds ambiguity rather than clarity.

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 (aggregate) and resource (HUD FHA multifamily mortgage maturities) plus the three grouping dimensions and the returned metrics. It is clear on its own, but it never contrasts itself with the sibling hud_fha_maturity_search, so an agent must infer that this is the aggregated view versus the record-level search.

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 concrete example questions ('which FHA lenders have maturities in 2027?', 'FHA maturity exposure by state') and an explicit out-of-scope list (default risk, ownership, borrower intent, refinancing likelihood), which meaningfully prevents misuse. It stops short of naming the alternative tool to use for record-level lookups.

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