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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: top_up_url is returned only under specific conditions and is the ONLY link to give for adding tokens. It slightly under-delivers on what happens when the account is unauthenticated or the call errors, but the top_up_url rule is exactly the high-value context an agent would otherwise get wrong.

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 verb and return values, then a WHEN block, then the critical top_up_url caveat, then the pricing pointer. Every sentence adds decision-relevant information; nothing repeats structured fields.

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?

With no parameters, no output schema, and a simple read operation, the description does the work the missing output schema would otherwise do by naming the returned fields (balance, plan tier, top_up_url). It covers triggers, return shape, and the one risky downstream action an agent might take.

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 zero parameters, so the baseline is 4. The description correctly spends no words on inputs and instead redirects to parameterized siblings (estimate_only: true for pricing), which is the right allocation of attention.

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+resource ('Returns the signed-in aicut account's token balance and plan tier') and enumerates both return values. An agent can immediately distinguish it from adjacent tools like list_models or get_video without opening a schema.

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 explicit WHEN triggers: before the first priced ask of a session, when the user asks what they have left, or after a generation fails for lack of tokens. It also routes to alternatives for pricing ('list_models, or estimate_only: true for audio'), covering both when-to-use and where-else-to-go.

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