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

With no annotations provided, the description carries the full burden of disclosure. It clearly states that the result is an association, not causation, that it is a historical observation from a specific public dataset (CFPB HMDA 2025), and that it is not a prediction. It also notes limitations (HMDA has no credit scores). All key behavioral traits are disclosed.

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?

The description is well-structured, starting with the key answers and NOT FOR section, then providing the specific statistic and data source. Every sentence adds value; nothing is redundant. The length is justified by the richness of the information.

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 no parameters, no output schema, and no annotations, the description is fully self-contained. It explains what the tool does, the exact output (variance decomposition with McFadden values), the data provenance, and limitations. No additional information is needed for correct invocation.

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 tool has zero parameters, so the description does not need to explain parameter meaning. The baseline of 4 applies, and the description goes beyond by explaining the output format and the context, which indirectly informs the user about what inputs would have been needed if any.

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 explicitly states the tool answers specific questions ('does it matter which lender you apply to', 'how much of a denial is the lender rather than the borrower', 'what is the Door Effect') and that it returns a variance decomposition with a concrete outcome (38% of explainable variation). It also declares what it is NOT for, distinguishing it from other tools that handle individual estimates or causal claims.

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?

Clear usage context is provided: it is for answering the named questions and for a historical, aggregate analysis. It explicitly says NOT FOR causal statements or individual estimates, which tells the agent when not to use this tool and implies using other tools for those cases. It also states the data source and that it is not a prediction about individual applications.

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