rent_increaseON/BC/MB rent-increase guideline and new rent, floored to the cent. capped:false = exempt unit.
| Name | Required | Description | Default |
|---|---|---|---|
| year | Yes | Guideline year, e.g. '2026'; unsupported = latest (shown in reply) | |
| province | Yes | Province whose guideline applies | |
| unitExempt | No | ON: first occupied on/after 15 Nov 2018. MB: exempt for a non-rent reason | |
| currentRent | Yes | Current monthly rent in CAD |
Changes observed during successful MCP inspections.
Input schema / properties / unitExemptAdded value: +{
+ "description": "ON: first occupied on/after 15 Nov 2018. MB: exempt for a non-rent reason",
+ "type": "boolean"
+}Input schema / properties / year / descriptionPrevious value: -"Guideline year, e.g. '2026'. An unsupported year uses the latest; the reply shows which."New value: +"Guideline year, e.g. '2026'; unsupported = latest (shown in reply)"Input schema / $schemaRemoved value: -"https://json-schema.org/draft/2020-12/schema"Input schema / examplesAdded value: +[
+ {
+ "currentRent": 2200,
+ "province": "Ontario",
+ "year": "2026"
+ }
+]Input schema / properties / province / descriptionAdded value: +"Province whose guideline applies"Input schema / properties / year / descriptionPrevious value: -"Guideline year, e.g. '2026'. Use the rent_increase tool's supported years if unsure."New value: +"Guideline year, e.g. '2026'. An unsupported year uses the latest; the reply shows which."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this as a safe read-only, closed-world, non-destructive operation, so the bar is lower. The description adds genuinely useful behavior: results are 'floored to the cent' and a 'capped:false' result means the unit is exempt, though the 'capped' field is never defined and no output schema exists to anchor it.
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 compact fragments with the province scope and rounding behavior front-loaded, and no filler wording. Its brevity dips into under-specification, which is better captured by completeness than by conciseness.
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 simple read-only calculator with fully documented parameters, the definition is close to sufficient, but a tool with no output schema should say what comes back (guideline percentage vs. new rent) and clarify the dangling 'capped' field referenced in the description.
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 100%, including enum values for province and an exclusiveMinimum on currentRent, so the schema already carries parameter meaning. The description adds nothing about the four inputs beyond a partial gloss on exemption, making baseline 3 appropriate.
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 (calculate) and resource (rent-increase guideline and new rent) scoped to ON/BC/MB, which an agent can distinguish from rent_vs_buy or property_tax among siblings. It stops short of naming siblings or contrasting them, so it is clear but not fully differentiating.
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?
Provides no when-to-use or when-not-to-use guidance, and names no alternative tool. The only conditional hint is 'capped:false = exempt unit', which describes an output field rather than when to call the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.