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

Annotations already declare readOnlyHint, idempotentHint, and closed-world behavior, so 'Read-only' is partly redundant. However, the description adds genuine substance annotations cannot: it discloses that full details for each place are returned plus computed summaries (cheapest per month/night, closest to beach, most bedrooms, most recently confirmed) and shared vs. exclusive amenities.

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 tight sentences, front-loaded with purpose and constrained by 'from search_properties' before the return-value detail. The trailing 'Read-only' duplicates the readOnlyHint annotation and the enumerated summary overlaps with the existing output schema, costing a bit of economy.

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 single-parameter, read-only comparison tool with a full output schema, the definition covers what it does, what the ids must be, and what the caller gets back. Minor gaps only: no mention of behavior for invalid or unknown ids, or whether results preserve input ordering.

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 the schema already enforces minItems 2 / maxItems 5 with an example format, so the baseline is 3. The description adds real meaning beyond the schema by constraining the ids to values obtained from search_properties, which is not encoded anywhere in the input 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 ('Compare places side by side'), plus the cardinality bound (2-5) and where the ids must come from ('from search_properties'). This cleanly distinguishes it from get_property (single) and search_properties (discovery) without needing to name them.

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?

The id provenance from search_properties and the 2-5 cardinality give clear usage context, implicitly steering agents here instead of calling get_property repeatedly. It stops short of an explicit 'use get_property when you only need one place' exclusion, so it is not fully at the 5 level.

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