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 real context: where the funds come from (added credit, approved refunds, adjustments) and the required credential ('Cotlet API key with access to this app'). It stops short of describing response shape or rate limits, but it meaningfully supplements the safety profile.

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?

Front-loaded with the primary purpose and the when-to-use guidance, and each sentence carries information. The opening phrase slightly overlaps with the following sentences (balance/refunds described twice), which is minor redundancy.

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 zero-parameter read-only tool with no output schema, the description covers what it returns, the source of funds, the required auth, and the call context. Return-value detail is adequate even without an output schema, though it could state units/currency or pagination if any.

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 tool takes no parameters, so the baseline is 4. The description correctly implies a no-argument call and adds nothing that would conflict with the empty schema.

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?

States a specific verb (get) and resource (account balance) and further scopes it to pending refunds and pending returns. It is the only balance-related tool in the pirate-ship family, so it is unambiguously distinguishable from siblings like get_shipment or list_shipments.

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?

Explicitly names when to use it ('Call it before buy_batch to see that the balance covers the batch') and identifies the sibling it pairs with. The condition that selects it is spelled out rather than left to inference.

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