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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds value beyond that: it is free of charge and available on every plan, which materially affects an agent's willingness to call it, and it previews the response contents (burn rate, projected run-out, hottest endpoints).

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?

One dense sentence plus two ultra-short qualifiers, all front-loaded with the resource before the details. The fragments 'Free.' and 'Every plan.' each carry decision-relevant information rather than filler.

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 zero params, rich annotations and an output schema in place, the description only needs to convey purpose and when to call it — both are present. Nothing an agent needs in order to invoke it correctly 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 baseline is 4 and nothing is left underspecified. The description correctly implies no arguments are needed by framing everything as properties of 'this API key'.

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 resource (this API key's plan) and enumerates exactly what comes back: credits used and remaining, burn rate, projected run-out date, RPM limit, top credit-consuming endpoints. That detail makes it unmistakable against siblings like market_summary or feed_health, which are data-query tools rather than account introspection.

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?

'Call it before a large job' gives an explicit trigger condition, which is real guidance rather than implied usage. It stops short of naming a when-not or an alternative, but no sibling overlaps in function, so there is little routing ambiguity to resolve.

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