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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), lowering the bar. The description adds a genuinely valuable nuance beyond the annotations: charge_off_rate is charged-off loan COUNT divided by total loan count, not dollar-weighted. This prevents a likely misinterpretation of a financial metric. No contradiction with annotations exists.

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 with no waste: core purpose, example queries, and the critical metric-definition caveat. The purpose is front-loaded, and every sentence earns its place without repeating schema or annotation content.

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, the combination of full annotation coverage and 100% schema coverage carries much of the burden. With no output schema, the description appropriately names the returned metrics (rate and dollar amount) and grouping dimensions. Minor gaps remain, such as return row structure and ordering, but the description adequately equips an agent for a correct call.

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 description coverage is 100%, so the baseline is 3. The description's "aggregated by NAICS code, state, lender, or program" echoes the group_by enum, and the example questions map loosely to parameters (state, naics_code), but no new parameter-level detail is added beyond what the schema already documents.

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 states a specific verb and resource: charge-off rate and dollar amount, aggregated by NAICS code, state, lender, or program. The aggregation dimensions clearly distinguish it from sibling tools like sba_loan_lookup (individual loans) and sba_largest_loans (loan amounts), while the example questions reinforce what the tool computes.

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 example questions ("which industries have the highest SBA loan charge-off rate", "charge-off amount by state") imply when this tool is appropriate, but the description never names alternatives or states when not to use it. With four SBA-related siblings present, explicit routing would have strengthened this dimension.

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