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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that — the data source ('HUD's active file'), the exact metric set, and the 12-month realized-rate benchmark — but leaves the benchmark's definition and the response shape unspecified.

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?

Two sentences, no waste, metrics front-loaded and the filtering behavior appended. Every clause carries information an agent needs.

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 enumerates the returned metrics, and annotations cover the safety/mutability profile. Minor gap: the '12-month realized-rate benchmark' is named but not explained, and the default unfiltered behavior is only implied.

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 50%, but the uncovered parameter (program) is enum-constrained and self-documenting, while state carries its own two-letter-code description. The description adds the key semantic point that both are narrowing filters and that omitting them yields whole-portfolio totals.

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 concrete verb+resource: totals and medians over FHA-insured apartment loans in HUD's active file, and enumerates the specific metrics (count, units, balances, median note rate, benchmark, breakdowns). That makes clear it is an aggregate/portfolio tool rather than a record lookup, though it never names how it differs from siblings like program_facts or size_223f.

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?

'Pass state or program to narrow it' implies the tool works at portfolio level and both filters are optional, which is useful. But there is no explicit when-to-use, no when-not-to-use, and no routing to search_loans/get_loan for loan-level data.

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