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

Beyond readOnlyHint, it discloses the accounting semantics that shape agent behavior: events count per delivery with large events billed per 64 KB, and each tool call that reads or changes the account counts as one API call — meaning the agent's own calls consume quota. It also states that each metric's reset time is included, which the annotations do not convey.

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 what the tool reports, followed by usage guidance, so the agent gets purpose before triggers. The enumeration is long but every clause names a distinct meter or counting rule, so little is wasted; it is dense rather than padded.

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?

There is no output schema, yet the description effectively previews the return payload (each meter plus its reset time), so an agent knows what it will get back. For a read-only, zero-required-param usage tool, nothing needed to call 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?

Schema coverage is 100%, so the single api_key parameter is already fully documented in the schema, including the HTTP-vs-stdio nuance. The description adds nothing about parameters; per the rubric, a fully documented single parameter lands at the baseline 3.

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 states a precise purpose — showing plan limits and consumption — and then enumerates exactly which counters are reported (events, overage, compute allowance and its consumers, API calls, code runs, snapshots, reset times). No sibling tool covers usage/limits, so an agent can identify it immediately.

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 three explicit invocation triggers: when something answers with a limit, before bulk work such as replay_failed, and when the user asks about usage. It even names the sibling (replay_failed) that should be preceded by this call, which is exactly the routing information an agent needs.

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