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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the keyless nature, the ability to call with no arguments to get a coverage report, and the dual-purpose behavior (coverage + code/query resolution), which enriches understanding without contradicting annotations.

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 front-loads the primary purpose, then details the questions answered, gives a usage hint, introduces the secondary use, and ends with examples. It is slightly long but every sentence carries information, and the examples are valuable. It could be trimmed slightly, but it is not verbose.

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, idempotent tool with three optional parameters and no output schema, the description covers the core usage scenarios, the input modes, and the fact that it is keyless. It does not describe the exact response format, but the 'Reports...' phrasing implies the output contains those fields, and the examples clarify expected calls. The description is adequate for an agent to use it correctly.

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% with descriptions for code, limit, and query, so the baseline is 3. The description adds the no-argument invocation (via the example ffiec_coverage({})) which implies that an empty call yields the coverage report, and it clarifies the relationship between code (resolve) and query (search). This extra context goes beyond the schema's per-parameter descriptions.

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 ('Report') and resource ('FFIEC call report data availability'), enumerating the exact content (quarters, banks, line items, schedules, filing lag) and the questions it answers ('what call report data do you have', 'how current is this', 'which quarters can I compare'). It also covers the secondary purpose of resolving MDRM codes or searching by description, making it clearly distinct from sibling tools like ffiec_call_report or ffiec_compare_banks.

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 tells the agent when to use it: 'Use before a trend question to see the window,' and it specifies the types of queries it answers. It also gives a second use case (resolving MDRM codes) and provides three concrete examples with different argument patterns. It does not name alternatives or state when not to use it, but the usage context is clear enough.

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