slice_costs

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

With no annotations provided, the description carries the full burden. It explicitly states 'This is read-only: it slices and charts cost data. It never changes anything.' It also describes the return format (numbers and a card for charting). However, it does not cover error handling, rate limits, or prerequisites (e.g., data ingestion), though for a read-only query tool, the provided disclosure is largely sufficient.

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 long but well-structured: purpose first, then parameter details, then example. Every sentence adds value. It could be slightly more concise (e.g., combining some dimension explanations), but for a tool with 12 parameters and 0% schema coverage, the length is justified.

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 (12 parameters, no output schema, no annotations), the description is highly complete. It covers all parameters, explains CUR vs focus behavior, and gives a usage example. It doesn't mention potential errors or pagination, but for a cost query tool, the core functionality is well-documented.

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, and it does excellently. It explains each parameter in detail: dimensions (with full list including Tags and line-item ones), filter/exclusion structure (with ops like eq, in, contains), metric options, granularity, order_by, dates, provider, and via. It even provides a concrete example. This adds immense value beyond the bare 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 clearly states the tool's purpose: 'Slice cloud cost any way you want' and describes it as a flexible, moldable cost query. It distinguishes from sibling tools like get_costs_by_service or get_cost_summary by emphasizing it's for ad-hoc queries instead of canned reports. The use of specific verbs ('slice', 'group and filter', 'returns both the numbers and a card') makes the purpose precise.

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 provides explicit guidance: it's for flexible queries 'instead of a fixed set of canned reports'. It explains when to use line-item dimensions (CUR pushdown) and gives an example query. It implies that for specific pre-defined reports, one should use other tools (siblings), but lacks an explicit 'do not use this for X' statement, which would elevate it to 5.

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