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

Beyond the readOnlyHint annotation, the description adds valuable behavioral context: never charges, works at zero balance, and clarifies that it does not behave like framefetch_extract. It also mentions top-up endpoints for low balance, adding operational transparency.

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 compact and well-structured: purpose first, then usage guidance, then return details. Every sentence serves a purpose, with no filler or 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?

Despite having no input schema or output schema, the description provides return fields (balance_micros, spend_7d_micros, calls_7d) with units and usage context. This fully covers what an agent needs to use the tool effectively.

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 has zero parameters, so per the rubric baseline is 4. The description adds no parameter-level detail because none is needed, but it does explain the return fields and units, which is useful despite not being parameter semantics.

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: 'Check this account's credit balance/usage.' It clearly distinguishes itself from sibling framefetch_extract by noting it is read-only and works at zero balance, unlike the sibling.

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?

Provides explicit when-to-use guidance: at session start, periodically, or after a 402. Also gives a clear when-not-to-use case (before every call in a tight loop), which is concrete and actionable.

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