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

Annotations already convey readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: data source (SBA Public Loan Disclosure Data), cost ($0.10 USDC per call), and an illustrative example of the output shape. It doesn't mention pagination or edge cases, but the added context is meaningful.

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 but information-dense: use cases, data contents, an illustrative example, source, and pricing—all in four sentences. Every sentence serves a purpose, and critical details (cost, source) are included without padding. Front-loading the 'Use when' clause helps rapid decision-making.

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 lists return dimensions (counts, amounts, average sizes, top lenders, industry concentration), which partly covers return values. Parameters are clarified via example and grouping language. It does not explicitly state behavior when no state/industry is provided (e.g., national aggregate), but for a read-only lookup tool the provided context is largely sufficient.

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 only 33% (industry has a description; year and state do not). The description compensates by explicitly naming 'state' and 'NAICS sector' as the grouping dimensions and providing a concrete example (Illinois manufacturing). It gives enough semantics for all three parameters despite the schema gaps.

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 the tool returns SBA 7(a) and 504 loan approval data with specific metrics (counts, amounts, average sizes, top lenders, industry concentration) by state and NAICS sector. The opening 'Use when' clause further anchors its purpose in concrete business scenarios, making it distinct from the long sibling list where no other tool targets SBA data.

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 provides explicit use cases: assessing lending opportunity, benchmarking bank production, evaluating CRA performance, and identifying unmet needs. It does not name alternatives, but since no sibling tool covers SBA lending specifically, the context is sufficient. It lacks a 'when not to use' note, which keeps it from a 5.

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