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

Annotations already declare readOnly/closed-world/non-destructive, yet the description adds real behavioral context: the required permission scope, the key-type nuance for enabling it, and the fact that the call is free. That goes beyond the annotation set, though it says nothing about rate limits or freshness of the spend figures.

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 returned data before the permission caveat, which is the right ordering. The permission sentence is long but carries needed auth detail; overall it is tight for the amount of information conveyed.

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 takes on the burden of describing the return shape and does so thoroughly (totals, per-platform split, call-status counts, discount, wallet entries). Combined with the auth prerequisite, an agent has enough to call it correctly; only sibling disambiguation 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% and both params are self-documented with defaults and bounds. The description only echoes them implicitly ('last N days', 'recent wallet entries') without adding format or interpretation beyond the schema, so baseline 3 applies.

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 (spend/billing) and enumerates exactly what is returned: total USD, per-platform breakdown, charged/free/failed counts, discount, and wallet ledger entries. It is clear what the tool does, though it never explicitly distinguishes itself from the closely related sibling everyinfra_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?

The description supplies the precondition for use (the account must hold 'billing:read', with detail on default vs product-line-limited keys) and notes the call is Free. However, it gives no guidance on when to pick this over everyinfra_usage or everyinfra_requests, so the choice between spend-reporting siblings is left to inference.

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