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

Annotations already establish the safety profile (read-only, idempotent, non-destructive, open-world). The description adds meaningful behavioral context by stating that it searches both names and instruction text, that it is keyless, and that it returns official names plus full reporting instructions. No contradiction with 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 front-loaded with the primary purpose, followed by useful context, natural-language examples, and a compact code example. Every sentence adds information, and the 'Keyless' note plus example calls are directly useful for an agent without adding filler.

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 simple lookup tool, this description is complete: it covers both lookup directions, the searched corpus (names and instruction text), the return content (official name and full reporting instruction), and access requirements (keyless). The schema covers limit behavior, and annotations cover safety, so an agent can correctly decide and invoke the tool.

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?

The schema already documents all three parameters with 100% coverage, so the baseline is 3. The description adds value by showing the two alternative call patterns ('code' vs 'query'), giving concrete examples like 'ACCT_010' and 'delinquent loans', and clarifying that queries target both names and instruction text.

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 opens with a specific verb and resource: 'Look up what an NCUA call report account code means, or find the code for a figure.' It clearly names the 5300 Call Report codes, gives example codes, and states the return content (official name and full reporting instruction), which cleanly differentiates it from sibling tools that focus on credit unions or branches.

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 provides strong context for when to use the tool: answering questions like 'what is ACCT_010', 'which account code is total assets', and 'what does NCUA count as a delinquent loan'. It does not explicitly name alternative tools or state when not to use this tool, but the account-code-specific scope makes the intended use clear.

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