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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. Beyond that, the description discloses provenance (real-estate board, CREA, CMHC, StatCan) and the conditional return behavior for metro-matched cities, which an agent needs to interpret the response. It does not state data freshness/currency beyond 'current', which is the main remaining gap.

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 dense sentences, front-loaded with the trigger ('Call this for...') followed by the payload. The metric list is long but each item earns its place by telling the agent what data comes back; the sources sentence is slightly trailing but useful.

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 carries the burden of describing returns and does so adequately, including the conditional CMHC/StatCan blocks. It omits units/currency and data-recency caveats, which an agent might still need for correct interpretation.

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?

Only one parameter (ville), and the schema already documents it at 100% coverage with matching city examples. The description adds no format, normalization, or matching-rule detail (e.g. how a city name is resolved to a covered metro), so the schema does the heavy lifting — baseline 3.

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 states a specific verb+resource ('current housing-market figures in a Canadian city') and enumerates the exact metrics returned (MLS HPI benchmark or median, YoY change, sales volume, months of inventory, DOM, 5-year growth). It is unambiguous against siblings like taux_courants or taxe_mutation, which cover different domains.

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?

'Call this for...' gives a clear triggering context, and the conditional clause tells the agent when extra CMHC/StatCan blocks appear (when the city matches a covered metro). No explicit exclusions or named alternatives are given, 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.