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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds genuinely non-structured context: the SBA PPP FOIA source, the as-of date (2024-09-30), and the exclusion of sole proprietors/individuals, which materially affects result interpretation.

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-loads what is aggregated and how it groups, then lists metrics, scope, and provenance in tight succession. The example questions are illustrative rather than filler, though the single dense paragraph is packed and slightly repetitive between the metric list and the example questions.

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 correctly enumerates the returned fields (count, approved, forgiven, forgiveness rate, jobs) and adds source and refresh date. Remaining gaps are minor: behavior on invalid state codes or ties in ranking is not addressed.

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 every parameter, including its default and enum values, is documented in the schema. The description reinforces that state is applied before grouping and that group_by covers industry/state/lender, but adds no syntax or constraints beyond the schema, so the baseline 3 is appropriate.

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?

States a specific verb (aggregate) and resource (PPP totals) plus the exact grouping dimensions and the metrics returned. It is clearly distinguishable from ppp_loan_lookup (per-loan retrieval) and the sba_* loan-level tools, since the agent can tell this is a grouped roll-up.

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?

Gives concrete example questions it answers and a clear scope condition (optionally one borrower state, business borrowers only, sole proprietors excluded). It stops short of naming alternatives for overlapping cases — e.g., grouping by lender versus sba_lender_league_table is not differentiated.

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