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

Annotations already declare readOnlyHint=true, so the safety profile is known Stephen. The description adds substantial behavioral detail beyond annotations: compare is required, `{}` auto-derives the previous window, filterCel omitted or "" is unfiltered (not AWS-only), and nestingEdges warns against summing hierarchical contributors. This addresses a subtle and likely accidental misuse (double-counting) that the schema would not reveal. No contradiction with 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?

The description is dense but every sentence serves a distinct purpose: purpose, prerequisite, constraint, a behavioral warning, a default preference, and two examples. There is no redundancy or filler. The structure naturally front-loads the core purpose and then progressively adds nuance, making it easy for an agent to scan.

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 8 parameters Prix, no output schema, and a non-trivial analysis workflow, the description covers everything an agent needs to invoke it correctly: required fields, ordering of discovery calls, column selection rules, filter semantics, aggregation defaults, and sample invocations. It even includes a hierarchical aggregation caveat that would otherwise be an easy to make error. The only thing missing is an explicit return format, but given the complexity handled and the annotations covering safety, this is complete enough.

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 ~88%, but the description goes beyond the schema to explain critical semantics: compare's `{}` shorthand, filterCel's unfiltered default, aggregationMethod's preference to omit, and the recommended 2–4 column range (with max 8). The examples demonstrate the exact structure for columns, including the { column, contains } object form. This is high-value practical context that the schema alone does not provide.

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 opening sentence states a specific verb and resource: 'Find which dimension values drove a cost change between two periods.' This clearly distinguishes the tool from siblings like query (raw data) or suggest_groupby (suggest dimensions), and it explicitly frames the tool as a before/after analysis. The name and description are aligned, and the purpose is immediately actionable.

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 gives explicit usage direction: 'Prefer suggest_groupby / search / get_context first, then pass 2–4 columns (max 8).' It tells the agent the prerequisite discovery tools Series and the recommended column count. It also provides a clear exclusion ('Do not invent columns') and clarifies filterCel semantics. The two concrete examples further illustrate both datePreset and from/to usage, leaving little ambiguity about when to call this tool.

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