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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantive behavior on top: determinism, that IRS limits are applied and cited in provenance, the combined 402(g)+414(v) catch-up ceiling naming in applied_caps, the front-load forfeiture risk surfaced by the default has_true_up=false, and the structured-error behavior of output='capture' on the hosted HTTP transport. No contradictions with annotations.

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-loads the disclaimer and one-sentence purpose before the capability list, and the output-mode guidance is placed at the end where an agent making the call will find it. The prose is dense and long, with some redundancy between the description and the schema's toolArguments text (the 402(g) catch-up and capture-transport caveats appear twice), but every section carries real information for a heavy calculator.

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?

There is no output schema, so the description correctly carries the return-value burden: it enumerates the headline scalars, notes that period_schedule is stripped in 'summary', and describes the capture_ref URI. Combined with the annotation coverage and full schema descriptions, an agent has everything needed to select the right output mode and interpret results.

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, but the description adds derived semantics beyond a plain field list: it explains the interaction between participant_age and the resulting applied_caps[].cap_name/limit_value, why has_true_up defaults false (conservative forfeiture modeling), and what each output mode does to the payload. It largely mirrors the schema's own param text, which caps the score below 5.

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 ('Deterministic 401(k) employer-match optimizer') and enumerates exactly what it computes: match captured, max entitlement, forfeited match, full-match threshold, front-load forfeiture, and a per-period schedule. This is unmistakably distinct from sibling calculators like calculate_emergency_fund or compare_strategies because the resource and outputs are named concretely.

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?

Gives clear operational context: which output mode to pick ('summary' default for headline scalars, 'inline' for the schedule, 'capture' for the file pipeline) and the transport restriction that capture is stdio-only. It also flags the tool as HEAVY and adds a 'calculation, not advice' caveat. It stops short of naming a sibling alternative or an explicit when-not-to-use condition, so it is context-rich but not fully routing.

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