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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to cover safety. It adds valuable behavior: return shape ('{ column } or { column, contains } plus metrics'), filterCel semantics ('omitted or "" is unfiltered (not AWS-only)', 'supports == null'), and a guard against inventing columns. However, it doesn't specify edge behavior like empty results or error conditions.

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 and front-loaded with purpose, then usage rules, then parameter nuances, then examples. It is longer than average, but each sentence conveys necessary operational detail and the EXAMPLES block clarifies real usage. The structure is logical, though the first paragraph could be slightly trimmed.

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?

For a tool with 6 parameters, a nested compare object, no output schema, and many sibling tools, the description covers triggers, parameter preferences, return shape, and downstream integration with find_cost_change_factors. Minor gaps remain: the exact output structure isn't fully enumerated and failure/empty-result behavior is unstated, but overall the agent has enough to call it 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 coverage is 83%, so the baseline lift is already high, but the description adds substantial semantic meaning beyond the schema: datePreset is preferred over from/to, compare `{}` auto-derives context, filterCel empty is unfiltered, and slug auto-detects while failing for multi-org accounts. These details help an agent construct correct arguments.

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 opens with a specific verb and resource: 'Suggest the best dimensions to group costs by, based on an optional filterCel (CEL).' It also states exactly when to call it ('when the user asks "what should I look at?" or when you need columns for query or find_cost_change_factors'), clearly distinguishing it from sibling tools like find_cost_change_factors and query.

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 explicit trigger conditions and decision rules: 'Prefer datePreset over from/to', 'Omit compare for current-window ranking', 'Pass compare ... when the user asks what changed', and downstream instructions to pass 2–4 returned columns into find_cost_change_factors. It also warns 'do not invent columns', which is crucial for correct invocation.

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