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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with them. It adds genuine value beyond the annotations by disclosing the data source (FFIEC official federal record), the per-call cost ($0.10 USDC), and the regulatory consequence timeframe. It doesn't cover auth needs, rate limits, or not-found behavior, but for a read-only lookup the added context is solid.

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 front-loaded with the 'Use when' usage trigger and efficiently packs the rating categories, source, and price. However, the Heartland Community Bank example and the 12-24 month delay detail are somewhat promotional and could be trimmed; for a one-parameter lookup tool the ~125-word description is longer than strictly necessary.

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 low-complexity tool with one required parameter, no output schema, and read-only annotations, the description covers the essentials: the rating scale implies what the response contains, the hour source and cost are disclosed, and the example hints at response fields (exam date, consecutive ratings). It doesn't specify exact response structure or not-found behavior, but nothing an agent needs to invoke it correctly is missing.

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?

With 0% schema description coverage for institution_name, the description carries the burden of explaining the parameter. It partially compensates — 'a bank's CRA track record' and the example 'Heartland Community Bank' imply the parameter is a bank name — but it never explicitly states the expected format (exact legal name, handling of subsidiaries) or valid values. This is partial, not complete, compensation.

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 the tool retrieves a bank's CRA performance ratings from the FFIEC CRA Ratings Database and lists the full rating scale (Outstanding, Satisfactory, Needs to Improve, Substantial Noncompliance). The resource is unmistakable and no sibling tool overlaps with CRA, though the description never explicitly names an alternative or uses an explicit verb like 'retrieve'.

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 enumerates when to use the tool: before a merger application, charter acquisition, branch expansion approval, or community lending partnership, and explains the regulatory stakes (a 'Needs to Improve' rating can delay or block approval by 12-24 months). It provides clear situational context but no when-not-to-use guidance or named alternatives, stopping short of a 5.

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