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

Annotations already declare readOnly/idempotent/non-destructive, so the description's value lies in return-shape disclosure, which it delivers: totals, category and payee breakdowns, and new/disappeared payee detection. Without an output schema, that enumeration is the only way an agent knows what comes back. The transfer-exclusion rule is an additional behavioral trait not present in annotations or schema.

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 the core action and return shape, then scope, then routing guidance. The parenthetical example ('am I spending more on X than last year') and the sibling routing sentence both earn their space; nothing is redundant with the schema.

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 six-parameter read-only analytics tool with no output schema, the description supplies the missing half: what is returned, what is excluded, and which sibling to use instead. An agent has enough to select and call it correctly, with only the period-ordering convention as a residual gap.

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%, so the baseline is 3; the description earns one more by explaining that category filtering is optional and that the default is all non-transfer categories. It does not clarify which of period A or B is the baseline/current period, so the direction of any 'more vs less' result is left to inference.

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 ('Compares spending between two date periods') and enumerates the outputs: overall totals, per-category, per-payee, and new/disappeared payees. The 'Excludes transfers' clause further narrows scope so an agent can distinguish it from month_end_review or get_trend_analysis without reading the schema.

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?

Names the alternatives explicitly and the conditions that select them: month_end_review for a single period's breakdown, financial_health_snapshot for a right-now check, and navigate_to_trends as the companion link. It also gives concrete use cases (month-over-month, year-over-year) that map directly to the required date parameters.

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