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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description focuses on what annotations cannot express: a token cost of 4 per call with refund rules that differ per layer (buildings never refunded, planning refunded unless covered). That is genuinely useful pricing behavior, though it does not describe response shape or failure modes beyond the cost model.

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 purpose, then the one-layer-per-call rule, then the sibling pointer, then cost. Efficient, but the twelve-layer enumeration duplicates the enum and adds length without new information.

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 no output schema, the description supplies enough to call correctly: which tool to use, that layers are fetched one at a time, and the cost/refund model. The per-layer return contents are covered by the enum description rather than the prose, which is an acceptable division of labor, though a one-line hint about what a layer result looks like would close the 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 67% and the enum's own description already documents each layer's contents and caveats in depth, so the description's listing of the twelve layer names largely repeats structured data. It does not explain the transactionId/transaction_id alias duplication or which id format source is canonical, leaving the one genuinely ambiguous parameter aspect to the 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?

States a specific verb and resource ('Detail of one layer for one transaction taken from a search result'), enumerates the twelve layers, and explicitly names the sibling tool it is not (get_parcel_report for a parcel without a transaction). An agent can distinguish it from search_transactions and get_parcel_report without opening a schema.

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 rule ('One layer per call - call again with another layer for more') and a clear exclusion with the correct alternative ('For a parcel without a transaction use get_parcel_report'). The routing condition is stated, not inferred.

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