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

Annotations already establish that this is read-only, idempotent, and non-destructive. The description adds genuinely new behavioral context: null means unknown, the comparison fails if any property is no longer public, and units are normalized to EUR/period/m2. This goes meaningfully beyond the structured 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?

Two front-loaded sentences with no filler. Each sentence earns its place: operation and scope, unit behavior, null semantics, and failure mode. The description is compact, scannable, and easy for an agent to parse.

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?

Although there is no output schema, the description covers the critical runtime behaviors an agent needs: unknown-value semantics, failure when properties are not public, and unit normalization. The exact return shape and locale effect are left implicit, but these are minor given the tool's straightforward comparison purpose.

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%, so the description must compensate. It adds meaning for 'ids' (distinct, public, 2–4 items), though the schema already encodes min/max. The 'locale' parameter is not explained, and the description does not clarify how locale affects output. Compensation is partial.

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 names a specific operation ('Compare'), a precise resource scope ('2–4 distinct public property IDs'), and the standardized comparison semantics ('same fields', 'explicit EUR/period/m2 units'). This clearly distinguishes it from sibling tools like get_property (single property) and search_properties (discovery).

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?

It clearly implies when to use the tool: when the agent has 2–4 known public property IDs and wants a uniform comparison. The failure caveat about properties no longer being public gives useful operational guidance. It does not explicitly name sibling alternatives, so it stops short of a 5.

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