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

Annotations already declare readOnly/idempotent/non-destructive, so the description focuses on the non-obvious semantics: a date range is aggregated into a single column set rather than a time series, and only_category_ids/group_ids are inverted by the app so the caller must pass what they want visible. Those two quirks would otherwise cause silent wrong results, and they are disclosed up front.

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?

Front-loaded with purpose, then selection criteria, then sibling boundaries, then the inversion caveat — a sensible priority order with no filler. It is dense and somewhat long, with mild repetition between the report-shape sentence and the example-query sentence, but every sentence carries usable information.

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?

All 11 parameters are schema-documented, there are no required params, and no output schema exists — so the description compensates by describing the rendered result (columns, subtotals, Net Income total), which is exactly the missing return-value context. Nothing material for correct invocation is absent.

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%, so the baseline is 3; the description earns a bump by re-emphasizing the counterintuitive inversion of only_category_ids and group_ids ('pass what you want visible') and by clarifying that widening date_range_key merely sums more into the same columns. It does not add meaning for nesting, roll_up, transfers, percentages, or the rollover flags beyond what the schema says.

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 and resource ('Deep link to the Income & Expense report (/income_expense)') and immediately defines what that report is: a budget-vs-actual P&L for one period. It then enumerates the output shape (Income/Expense sections, one row per category with Budgeted/Actual/Difference, subtotals, Net Income), which makes it unmistakable against siblings.

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?

Explicitly names the selection condition ('Pick this for breakdown / where-did-it-go asks') and gives four concrete example utterances. It also routes away to three named alternatives (navigate_to_trends for one category's trend, navigate_to_budget for budget management, navigate_to_transactions for raw transactions), so both when-to-use and when-not-to-use are covered.

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