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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses the USD unit convention, the top-level currency field, the native_cost/native_currency reconciliation exception, an explicit prohibition on summing or comparing native_cost across rows, and the absence of a cost_metric parameter (cost is always billed, never amortized). This is unusually rich behavioral context.

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 purpose, then alternative routing, then unit conventions — a sensible order with no filler sentences. It is on the long side for a two-parameter read tool, and the currency rules could be tightened, but every clause carries information.

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 helpfully describes the return shape (per-row cost, top-level currency, native_cost/native_currency). The main gap is the date parameter format; otherwise an agent has enough to call and interpret the tool correctly.

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 description coverage is 0% for both startDate and endDate, so the description must compensate. It conveys that the pair forms a 'date range' but never states the expected format, inclusivity, or defaults, so the agent still has to guess the string syntax. Partial compensation only.

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 and resource ('Fetch raw per-service cost entries ... unaggregated') and immediately distinguishes itself from the sibling query_costs by scope (individual rows vs. bucketed/aggregated spend). An agent can route between the two without opening either schema.

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?

Explicit when-to-use and when-not-to-use: 'Prefer query_costs for time-bucketed/aggregated spend — this is for inspecting individual rows.' It names the alternative and the condition that selects it, leaving nothing to inference.

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