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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds behavioral nuance beyond that: that open can still fail after approval and that the tool is deliberately a separate state to avoid misreading an approved application. It does not cover edge cases like pending states in detail, but the key behavior is disclosed.

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?

Three sentences, each carrying meaningful information and the primary purpose is front-loaded. The second and third sentences partially overlap in their warning about application status, but the additional lifecycle context is valuable rather than redundant waste.

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?

Given a high-coverage input schema, an output schema, and non-destructive read annotations, the description provides enough context—states, the distinction from application status, and the failure-mode rationale—for an agent to call it correctly. It doesn't need to list return fields because the output schema already does.

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?

Input schema has 100% description coverage for the single parameter, so the description need not compensate; comparison establishes the baseline 3. The description adds only a general implication that applicationId refers to the banking application. No deeper parameter semantics are introduced, which is fine since the schema covers it.

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?

Description states a precise verb and resource: reports the state of an application's deposit account, with enumerated states (queued, being opened, open, could not be opened) and the last four digits. It also explicitly distinguishes itself from the application's status, so the agent can separate it from banking_get_banking_application.

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?

Gives an explicit when: 'a caller that wants to tell somebody they can receive money must read this,' and a when-not: 'not the application's status.' It explains the approval-vs-opening lifecycle so an agent knows why this tool, and not a status tool, is the correct source of truth.

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