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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds valuable behavioral context: results are per-currency and must not be summed across currencies, and the scope defaults to completed statements. It also clarifies that credits/quotas are not transactions, preventing misuse. It does not cover edge cases like empty results, but that's minor given annotations.

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?

Three sentences, each with a distinct purpose: core function, currency caveat, and scope/defaults/alternative. It is front-loaded with the most critical information, and every sentence earns its place without redundancy. No fluff or 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?

Given the tool's complexity (nested objects, many sub-fields, output schema), the description covers the key aspects: what it does, default scope, currency warning, and when to avoid it. The 'filter' parameter is not mentioned, but the schema provides its structure. The output schema handles return values. Overall, it is sufficiently complete for an agent to safely invoke it, with minor gaps around filter usage.

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 0%, so the description must compensate. It does add meaning for 'metric' by listing the available enum values and for 'scope' by explaining its purpose (narrow to accounts/products and date range). However, it completely omits the 'filter' parameter, which has many useful sub-fields (text, category, currency, etc.) that an agent would need to know. The schema itself is detailed, but the description leaves a significant gap in parameter understanding.

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 clearly states it computes a single metric (sum/average/count/max/min) over a filtered set of transactions. It specifies the verb 'compute', the resource 'transactions', and distinguishes from siblings like get_credits explicitly. The scope and per-currency behavior further clarify its role, making it unambiguous.

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?

The description explicitly directs users to get_credits for non-transaction queries like credit quota or remaining pages. It also explains the default scope (all completed statements) and how to narrow via 'scope' with accounts/products and date range. This gives clear when-to-use and when-not-to-use guidance, naming an alternative.

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