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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantial context beyond them: the data source (public CFPB HMDA 2025 record, actions 1,2,3; loan_type 2), the sampling frame (95 of the 100 largest lenders that report reasons), and the semantic caveat that reason fields are not a partition and shares need not sum to 100. It also clarifies the output is an observation, not a prediction.

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?

Front-loaded with the questions answered and the single parameter, followed by the exclusion and provenance. Dense but each sentence carries information; the licensing/attribution line is boilerplate but required for use of the source data.

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 still specifies the returned quantities (median and max share per reason, top lender per reason) and the key interpretation caveat about shares not summing to 100. An agent has everything needed to call and interpret it 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?

Schema coverage is 100% and there is a single optional param, so the baseline is 3. The description adds meaning beyond the schema by explaining the effect of omitting lender (cross-lender medians) versus supplying one, which an agent would otherwise have to infer.

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 concrete questions it answers and then states precisely what it returns: median and maximum share of each HMDA denial reason across the reporting largest lenders, plus the lender carrying the highest share of each. This is a specific verb+resource and distinguishes it from siblings like get_lender_denial_stats and get_state_denial_stats.

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?

It gives explicit usage: pass optional lender, omit for cross-lender medians. It also states an exclusion ('NOT FOR: why a particular application was denied') and the analytical boundary (historical observation, not a prediction about any individual application). Nothing about when to choose this over siblings is left to inference.

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