get_cost_and_usage

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds date inclusivity ('Start date is inclusive, end date is exclusive') and says grouping/filtering are supported, but these largely repeat schema descriptions. It omits output shape, pagination, error behavior, rate limits, or any constraints on the query window, which leaves meaningful behavioral gaps for a 6-parameter tool.

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, front-loaded with the core purpose, then capabilities, then usage context. Each sentence earns its place: the first identifies the resource and action, the second conveys grouping/filtering power, and the third gives both a date-semantics detail and a clear 'when to use' signal. No fluff or repetition beyond acceptable reinforcement.

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 and no annotations, the description must compensate by explaining what the tool returns and any operational limits. It covers what the tool does but not the structure/format of its response, potential result sizes, or failure modes. For a tool with 6 parameters and nested object schemas, this is a significant completeness gap.

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 100%, so the baseline is 3. The description adds a few examples of valid group_by keys (SERVICE, USAGE_TYPE, REGION, LINKED_ACCOUNT, or cost allocation TAG), but these overlap with the schema's existing enum/description text. It does not meaningfully explain metrics, granularity trade-offs, or filter syntax beyond what the schema already provides.

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 ('Query') and resource ('AWS cost and usage for account 135709585800') and highlights key capabilities: grouping, filtering, and time period. It also positions itself as the primary tool for spend analysis, which distinguishes it from siblings like get_cost_forecast, get_cost_anomalies, and describe_budgets.

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?

Provides clear use-case context via 'This is the primary tool for spend analysis: monthly trends, per-service breakdowns, daily spikes, etc.' This tells the agent when to reach for this tool among siblings, but it does not explicitly state when not to use it or name alternative tools for non-spend-analysis needs.

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