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

With no annotations, the description carries the full burden and does well: it makes clear this is a non-mutating read scoped to the API key's owning account, and it states what information is returned. It stops short of richer context such as whether the balance is cached or when it refreshes, which keeps it out of the top score.

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?

Two sentences, no filler. The return value is front-loaded and the usage triggers follow immediately.

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 tool with no output schema and no annotations, the description supplies everything needed: what it returns, whose account it reflects, and when to invoke it. Nothing required for a correct call is missing.

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 schema cannot be misinterpreted and the 4 baseline applies. The description correctly adds no parameter discussion, matching the empty input 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?

The description names a specific verb+resource ('Returns the credit balance of the account that owns the API key') and adds the secondary payload ('plus where to get more'). No sibling tool in the set touches account credits, so the agent can distinguish it immediately from convert_file, get_job_status, etc.

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?

It gives explicit trigger conditions: call when a conversion fails with 'no credits' or when the user asks how many conversions remain. There is no when-not guidance or named alternative, but no sibling offers balance data, so a real alternative clause is not needed.

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