fdic_risk_ratios

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: the null-never-0 convention, the CBLR 0→null mapping, the exact totalAvailable semantics, the 'no ratio is recomputed' guarantee, and the note that these are regulatory metrics not a soundness rating. It also discloses the keying on CERT rather than SAM UEI/DUNS. This is rich, honest behavioral disclosure that goes far beyond what annotations provide.

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 dense but well-organized: it front-loads the core purpose and required input, then uses labeled sections (★UNITS, ★NULL-NEVER-0, HONESTY, NOTE) to convey critical caveats. Every sentence earns its place — the units warning, the null convention, the CBLR artifact, and the honesty contract are all essential for correct use. It loses one point because the density is high and the CBLR explanation is somewhat intricate, but the structure (labeled callouts) mitigates this.

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 data-fetch tool with 100% schema coverage, no output schema, and rich annotations, the description is complete. It covers the input contract, the output shape, the units, the null semantics, the pagination envelope, the error behavior, and the regulatory caveat. An agent has everything needed to call this tool correctly and interpret the results without guessing. The sibling context (fdic_search_institutions for cert lookup) is also provided.

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 schema already documents all 6 parameters. The description adds meaningful semantics beyond the schema: it explains that `cert` comes from fdic_search_institutions, that `reportDate` maps to REPDTE and omitting it yields the full time-series, that `limit` is capped at 1000, and that `sortBy` values map to specific fields (REPDTE/ROA/ROE/RBCRWAJ/EEFFR). It also clarifies the return shape. The only minor gap is that the description doesn't restate the default values for limit/offset/sortOrder, but those are in the schema. A 4 is appropriate because the description adds real semantic value on top of a fully-covered schema.

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 ('returns FDIC risk ratios'), a precise resource ('ONE institution by certificate number'), and the exact data source (api.fdic.gov/banks/financials). It enumerates the ratio families (profitability, net interest margin, efficiency, asset quality, capital adequacy) and distinguishes itself from sibling tools by emphasizing 'ONE institution' and the keyless FDIC endpoint. This is unambiguous and clearly differentiated from fdic_institution_financials and fdic_industry_summary.

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 explicitly states the required input (`cert` REQUIRED, sourced from fdic_search_institutions), explains when to omit `reportDate` (for full quarterly time-series), and provides the exact envelope semantics (only honest empty is meta.total:0/data:[]; any other envelope THROWS). It also gives a clear exclusion: CBLR banks do not report risk-based capital ratios, so the tool maps 0→null for both tier1RiskBased and totalRiskBased. This is explicit when-to-use and what-to-expect guidance.

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