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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the agent knows this is a safe, closed-world calculation. Beyond that, the description adds real value by disclosing the calculation model — HST is netted against the new-housing rebate, financing cost derives from a draw schedule, contingency applies to hard+soft costs. It does not describe the returned figures' structure, though no output schema exists to cover that 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?

A single front-loaded sentence with a colon-and-list structure; every clause names a distinct cost or return component and none is filler. It is dense but appropriately sized for a 14-parameter composite calculator, with only the missing action verb ('calculates') as a minor structural gap.

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 14-parameter, no-output-schema calculator, the description covers what goes in and what comes out at a component level, which is roughly adequate. It leaves unaddressed how the result is shaped (a single object? line items?), whether figures are CAD, and the preconditions tying ownsLand to landPurchasePrice — meaningful gaps when there is no output schema to lean on.

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% and every one of the 14 parameters carries its own description, defaults, enums and bounds, so the baseline is 3. The description adds only marginal parameter meaning — it implies projectType drives the HST rebate and that land transfer tax is a function of province — without explaining units, interactions (ownsLand vs. landPurchasePrice), or which inputs feed which outputs.

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 concrete artifact ('development pro forma for a Canadian build') and enumerates exactly what it computes: land, land transfer tax, hard/soft costs, HST net of the new-housing rebate, financing, contingency, sale proceeds, profit, margin, ROI. That is far more specific than a tautology and clearly separates it from single-purpose siblings like land_transfer_tax or closing_costs. It stops short of explicitly naming which sibling tools it replaces.

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?

Usage is only implied by the phrase 'for a Canadian build' and by the computed-output list, which signals whole-project feasibility analysis rather than a single-fee lookup. There is no explicit when-to-use statement, no when-not (e.g., existing-property purchase analysis), and no routing to alternatives such as closing_costs, land_transfer_tax, or renovation_roi.

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