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

Annotations already declare read-only, idempotent, non-destructive, so safety is covered; the description goes further by disclosing default traversal depth, that search scans the entire subtree rather than one level, and the exact payload fields (alias, parent, storage type, child count, cubes used in). It also notes the top member can be empty, which explains an otherwise surprising empty result.

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 the core behavior and return content, then usage, then the motivating example. Three dense sentences with little waste, though the NSP_Total Class illustration is narrow and could be 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?

With 8 parameters, no output schema, and rich annotations, the description supplies return fields, defaults, search semantics, and a concrete workflow link. Connection/application defaulting and limit paging are left entirely to the schema, which is acceptable but the only remaining 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 coverage is 100% and every parameter already carries a description, so the description only reinforces depth-vs-search interaction and member defaults that the schema also states. Baseline 3 is appropriate since the schema does the heavy lifting for all 8 parameters.

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 (lists members below a member of a dimension) with real scope detail: children by default, deeper levels with depth, plus the returned attributes. It never names the near-synonym siblings (find_members, get_dimension_metadata), so the boundary with those tools must be inferred from the description's hierarchy framing.

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?

Gives an explicit usage trigger: find exact member names before calling export_data_slice, with concrete examples (Scenario, Version, Currency members that hold data; locating a total when the top member is empty). No exclusion or explicit alternative routing is offered, so an agent picking between this and find_members is on its own.

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