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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavioral information beyond them: unpublished figures (e.g., 2027 plan limits as of 2026-11-02) return as null rather than being estimated, which is exactly the kind of caveat an agent needs to interpret results.

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?

Two dense sentences that lead with the comparison output and follow with the null-handling caveat; the figure list is long but readable and materially useful. Nothing is redundant with the title, though the enumeration could be trimmed slightly.

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 correctly carries the burden of describing return content (side-by-side dollars and percent change) and null semantics, so an agent knows what to expect. The remaining gap is edge-case behavior for invalid or reversed year pairs, which is not addressed in either the schema or the description.

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 50%, but the undocumented parameter (to_year) is a $ref to from_year, which is itself described as 'Calendar year: 2025, 2026 or 2027.' The description reinforces the two-year scope but adds no new semantics, such as whether reversed years are rejected or whether a one-year range is legal (the schema imposes no ordering constraint).

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 gives a specific verb and output shape ('Shows each retirement, IRA, HSA and Social Security figure for two years side by side with the dollar and percent change') and enumerates exactly which figures are covered. It is clearly a comparison tool rather than a single-value lookup, but it never names the sibling tools (get_contribution_limits, get_social_security_cola) that would be the obvious alternative for a one-year query.

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: an agent can infer this is the tool for two-year comparisons while the siblings retrieve single values. There is no explicit 'use this when / use X instead when' statement and no mention of prerequisites such as whether prior-year data must already be cached.

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