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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: NULL limits or a missing budget row mean unlimited, and keys are strictly scoped to their own row. It does not discuss pagination or response shape beyond the counter list, so 4 is fair.

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-loads the core action and result set, then adds the two constraints (NULL = unlimited, own-key-only) and the tier. Dense but every clause carries information; only the parenthetical rule reference (I-3) is arguably overhead.

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 output schema, the description carries the burden of explaining return values and it does so: it names the limit counters and the spend comparison, defines the NULL/missing-row unlimited semantics, and bounds visibility. An agent has everything needed to call it and interpret the result.

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?

Zero-parameter tool, so the schema-based baseline is 4. The description usefully frames what the caller implicitly scopes to (this credential's key) and what the returned counters mean, which is the only parameter-like semantic that matters here.

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 (Read) and resource (THIS credential's per-key action budget), and enumerates exactly which counters are returned (sms, invites, payment-request cents, dispatch, human pages) plus today's spend. The emphasis on 'OWN' and 'never another key's' clearly separates it from generic usage/report siblings like tascan_get_usage.

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 clear context for when this applies: it is a read-tier call returning this key's own budget, and it explicitly states the hard constraint that no key can read another key's row. It does not name an alternative tool or when-not-to-use it (e.g., vs. tascan_get_usage), so it falls just short of a 5.

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