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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on substantial extra context: the 'rough' confidence threshold at 6 months, that home_equity is always populated and independent of the user's setting, that negative values mean underwater, and that empty:true is a normal data-absent state with a message and next_step_url rather than an error. This is exactly the beyond-annotations detail the dimension rewards.

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?

The first few sentences are front-loaded and efficient, describing the return payload well. The back half, however, repeats the same property-setting instruction four times ('never override it', 'still say so plainly', 'Never imply the user has no property', 'offer to include property'), which bloats a tool whose only input is one optional integer.

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 capably (net_worth, home_equity semantics, forecast, empty case). Minor gaps remain: the forecast field names/shape, the default value of 'months', and any response-size behavior are unspecified.

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% for the single 'months' parameter, so the baseline is 3, but the description adds a genuine semantic tie-in: fewer than 6 months of history degrades forecast confidence to 'rough'. That is meaningfully more than the schema's bare 'How many months of history to include'.

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 opening sentence gives a specific verb and resource ('Returns the user's monthly net-worth history plus a linear forecast') and even specifies the forecast horizons, so an agent immediately knows the scope. It implicitly differs from the snapshot-style sibling get_net_worth, but no sibling is ever named, so the differentiation is left to inference.

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 description is heavy on how to *present* results (respect the setting, give counterfactuals, don't imply no property), but never says when to call this tool versus get_net_worth, project_retirement, simulate_scenario, or get_wealth_percentile. Usage selection is only implied by the tool's content.

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