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

Annotations already declare the tool read-only, idempotent, open-world, and non-destructive. The description adds valuable behavior: amounts are in whole US dollars normalized from thousands-files so they align with the NCUA pack, ranking vs. comparison behavior, and a 'Keyless' note. This goes beyond the annotations without contradicting them.

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?

Every sentence earns its place: purpose, natural-language queries, two calling modes, normalization detail, worked examples, and auth note. The content is front-loaded and dense without fluff, and the example calls make usage instantly clear.

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 6-parameter tool with no output schema, the description covers its main operation modes, normalization, examples, and authentication. It does not describe return values or error cases, but the examples and mode explanation are sufficient for correct invocation.

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 genuine semantic value by mapping metric examples to parameters, clarifying that names/certs select comparison while omitting them triggers ranking, and giving full example calls. This is more than the schema alone provides, though quarter semantics are left to the 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 starts with a clear verb+resource: 'Compare or rank US banks on a call report figure', and immediately gives concrete examples ('largest by assets, most deposits, highest net income'). It differentiates from sibling tools like ffiec_search_banks by framing this as a compare/rank operation, not a search or lookup.

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 explicit usage modes: pass names/certs to compare a specific set, or omit them to rank the whole industry, optionally restricted by state. It includes representative example calls. However, it does not explicitly contrast with alternatives like ffiec_search_banks or ffiec_call_report, so exclusion guidance is absent.

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