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

Annotations already cover safety (readOnly, non-destructive, idempotent), and the description adds meaningful behavioral context beyond those: it explains that 'lender' means different entity types depending on program, which materially affects interpretation of results. It does not describe output shape or ranking tie-breaking, but the annotation coverage lowers the bar here.

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 compact and front-loaded with the core purpose in the first sentence. The second sentence earns its place by defining lender semantics and giving concrete user-intent examples. There is no filler or redundancy.

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?

For a read-only aggregation tool with four fully documented optional parameters and no output schema, the description covers the key selection and invocation needs: what it ranks, how lender identity varies, and what kinds of questions it answers. It does not specify return structure, but that is not required given the tool's simplicity and schema coverage.

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%, so the baseline is 3. The description adds value beyond the schema by explaining the program-dependent meaning of 'lender', which is directly relevant to the program parameter, and by embedding example usage of state, program, and NAICS. This elevates it slightly above baseline.

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 clearly states a specific verb and resource: it ranks lenders by SBA loan count and total dollar volume. It also clarifies the key entity distinction between 7(a) originating banks and 504 CDCs, which helps an agent know what the tool returns. However, it does not explicitly differentiate itself from nearby SBA sibling tools such as sba_largest_loans, so it falls just short of a 5.

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 gives concrete example queries ('which bank does the most SBA lending in NAICS Y', 'top SBA 504 lenders in California') that signal when this aggregating/ranking tool is appropriate. It does not explicitly name alternatives or state when not to use it, so there is clear context but no exclusions.

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