Get Core Lmi Dimension

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description correctly spends its words elsewhere: the warning to reuse child codes exactly including leading zeros, and the note that metadata pagination is local rather than server-driven. Both are operational gotchas not recoverable from the annotations. The phrase 'metadata pagination is local' is terse and could be clearer about what actually gets paged.

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 short sentences with zero filler, front-loaded with the capability before the caveats. The density occasionally costs clarity, but nothing is redundant or padded.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile, which lowers the bar. Still, for an 8-parameter tool with 0% schema coverage, the description leaves version, level formats, and pagination range/defaults entirely to the schema, so an agent cannot fully reason about arguments from the text alone.

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 0% across 8 parameters, so the description carries the full burden and only partly discharges it: it names search, level, and aggregation_path and explains their mutual exclusivity, and 'pagination' implicitly points at limit/offset. It says nothing about the accepted format of aggregation_path, what values level takes (there are no enums), or the role of version, leaving several parameters semantically bare.

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: 'Find valid dimension codes', and it distinguishes two retrieval modes (name/code search vs. hierarchy browse via level and aggregation_path). It never names a sibling such as get_core_lmi_metadata or list_core_lmi_datasets, so an agent must still infer which tool to reach for, but the purpose itself is unambiguous.

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?

'Search and hierarchy filters are separate modes' is a genuine usage constraint that tells the agent not to combine search with level/aggregation_path. However, there is no guidance on when to prefer this tool over get_core_lmi_metadata or the dataset-listing siblings, and no prerequisites or exclusions are stated.

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