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

Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is lower, and the description adds real context beyond them: a default of 6 months, valid month windows (3/6/9/12), integer minor units with an example, and the family-timezone budget-period definition. It does not describe the response shape, but with no output schema that is a modest gap against an otherwise informative disclosure.

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 units/dates/periods sentence is dense but every clause pays off, and the drill-down condition is front-loaded. The metaphorical opener ('family portrait') and the vague title cost clarity without adding information, and the whole thing is delivered as one long block rather than clearly separated concerns.

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 read-only summary with no output schema, the description covers the important mechanics an agent needs: default window, allowed months, unit and date conventions, and the two modes (aggregate vs. drill-down). The remaining gap is the absence of any hint about the returned structure, which matters somewhat given no output schema exists.

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 0%, so the description must carry the load, and it does: months is constrained to 3/6/9/12 with default 6, key is described as 'a bill', and categoryId/irregular are described as selecting the entries behind a single number. That compensates well for the undocumented schema, though it doesn't state what happens if multiple selectors are combined.

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 says it produces a multi-month retrospective covering committed bills, spending, income, leftover, changes and habits, which conveys the resource. But the framing ('family portrait', title 'The usual month') is metaphorical rather than a clean verb+resource, and it never distinguishes itself from siblings like get_analytics, get_overview, or get_budget that an agent must choose between.

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?

It gives conditional usage for the drill-down path ('With key (a bill), categoryId or irregular: the entries behind that one number'), which is genuinely helpful. However it never states when to prefer this tool over get_analytics/get_overview/get_budget, so the primary routing decision is left to inference.

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