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

With no annotations, the description carries the full burden. It discloses the tool returns only an eligibility decision (no payment side effect) and describes the watch-only mode behavior ('we always allow and tell you what would have been stopped'). This goes beyond a generic 'check' and signals it is non-destructive. It doesn't explicitly state auth requirements or that it never executes a payment, but the contrast with card_get_virtual and the 'safe to call' wording make this clear enough.

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 front-loaded with the core purpose and then adds usage guidance and edge-case behavior. It is slightly wordy (the first two sentences are similar), but every sentence contributes meaning: scope, output, when to use, alternative, and watch-only safety. No filler, though it could be tightened slightly.

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?

Given no output schema, the description compensates by stating the return shape ('allowed or not, and which limit or rule stopped it'). It covers the key use case, prerequisites (watch-only mode adds a safety net), and differentiates from the payment card tool. It does not describe how to construct the nested payee/amount objects or the exact response format, but the schema and the high-level output hint are sufficient for correct invocation in most agent workflows.

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 60%, with some parameters (payee.ref, intent, idempotency_key) already described. The description adds context that amount and payee are used to assess limits/rules, and that replies are idempotent for the same payment. However, it doesn't elaborate on structure for nested objects (e.g., how payee.name/category or amount.value/currency are interpreted) or on the format of the idempotency key beyond what the schema says. This is adequate but not a strong supplement to the 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 opens with a clear verb and resource ('Check your budget before you buy') and then specifies exactly what it checks: 'daily spend limit and the procurement rules your owner set.' It states the output ('allowed or not, and which limit or rule stopped it') and differentiates from card_get_virtual, a key sibling. An agent can tell this is an eligibility check, not a payment tool.

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?

Explicitly states when to use: 'Use this when you already have a way to pay and only need to know if you are allowed.' It names the alternative, card_get_virtual, for when a card is needed. It also covers a special case (watch-only mode) and explicitly says it's safe to call before checking is enabled, leaving no ambiguity about prerequisites.

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