List covered FHA lenders sorted by denial rate or volume (2025 span: 1.8% to 78.7%). Historical observation computed from the public CFPB HMDA 2025 record (actions 1,2,3; loan_type 2). Not a prediction about any individual application. Attribution: FinanceRateCalc, CC BY 4.0.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
It discloses that data is a historical observation from the CFPB HMDA 2025 record with specific action/loan_type filters, and explicitly says it is not a prediction about individual applications. This addresses potential misinterpretation. However, it doesn't describe response structure or pagination, but the non-predictive caveat is strong.
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, each with specific content: list purpose, data source/caveat, and licensing attribution. No wasted words.
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 the tool's simplicity (two optional params, no output schema), the description covers the essential facts: what it lists, sorting options, data provenance, and a critical caveat. It could be enhanced by hinting at the returned fields, but the agent has enough to invoke correctly.
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?
The description explains the sort parameter's semantic (denial rate or volume) which aligns with the enum values. The limit parameter is not mentioned in the description; with 0% schema coverage, the agent must infer its meaning from the name and schema constraints.
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 opens with 'List covered FHA lenders sorted by denial rate or volume,' which clearly states the action (list), the resource (covered FHA lenders), and the sorting criterion. This distinguishes it from sibling tools that provide aggregate statistics rather than lender-level listings.
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 a ranking use case but does not explicitly state when to choose this tool over get_lender_denial_stats or the state/national stats tools. No exclusions or alternative recommendations are provided, so guidance is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct data scope: national, state, lender, metro gap, door effect, lender listing, and claim certification. The purposes are clearly separable even though several tools concern FHA denial statistics.
Tool names follow a consistent verb_noun snake_case pattern: get_* for retrievals, list_lenders for enumeration, and check_claim_contract for validation. There are no convention clashes or vague single-word names.
Seven tools is well-scoped for a focused statistics and claim-validation server. Each tool serves a distinct purpose and none feel redundant or bolted on.
The surface covers the main read-only operations: national, state, lender, metro, and door-level stats plus lender listing and claim contract verification. Minor gaps include retrieval of full contract metadata or other statistic categories, but core workflows have no dead ends.