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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safe read nature. The description adds valuable behavioral context beyond annotations: output is 'labeled, never as raw account codes' and the tool is 'Keyless'. This gives agents confidence about the return format and authentication. No contradictions found.

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 well-structured: it opens with the core purpose, then usage guidance, then parameter semantics, and ends with an example and keyless note. Each sentence earns its place, and it avoids repeating schema details. Slightly longer than the minimal, but the added examples and clarifications justify the length.

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 carries the burden of explaining return values. It states the output is 'labeled, never as raw account codes', which gives a sense of the data format. It covers the two main invocation patterns and the metric list. However, it does not mention pagination, time range parameters, or response size, which could be relevant for a long time-series query. Still, the description is sufficient for an agent to call the tool correctly in most cases.

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% for all three parameters, setting a baseline of 3. The description adds substantial semantics: it enumerates the accepted `metric` values, explains that omitting `metric` returns all figures for the latest quarter, and gives a concrete usage example with `name` being a fuzzy string. This meaningfully exceeds what the schema provides.

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 a specific verb and resource: 'Get one US credit union's reported call report figures over time, or every figure for a single quarter'. This precisely distinguishes it from sibling tools like ncua_credit_union_profile (likely a snapshot) or ncua_industry_totals (aggregate). The scope is unambiguous.

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 says 'Use for trends' and provides three concrete example queries, plus explains the two modes (pass `metric` for one series or omit for all figures in the latest quarter). It does not explicitly name alternatives when not to use this tool, but the usage context is clear and directive. A small gap is the absence of explicit exclusions for sibling tools.

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