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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description doesn't need to restate safety. It adds real value by disclosing the return shape — years until depletion or that growth covers it, the never-depletes monthly amount, a range and a year-by-year table — which matters because no output schema exists. The closing "estimate, not financial advice" caveat also sets expectations about precision, though it doesn't discuss edge cases such as zero-growth or withdrawal exceeding balance.

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?

Purpose and trigger examples are front-loaded, followed by return values and then exclusions, which is a sensible order. The long enumeration of user phrasings is justified as routing signal, but it is dense in a single paragraph and could be trimmed slightly without losing coverage.

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 four-parameter, read-only calculator with no output schema, the definition covers purpose, triggering questions, exclusions, what is returned, and an accuracy disclaimer. An agent has everything needed to select and call it correctly; nothing material is missing.

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 every parameter including defaults and bounds is already documented in structured data. The description adds only indirect hints — "monthly withdrawal" maps to monthlyWithdrawal and "the 4% rule in reverse" gestures at realReturnPct — but gives no guidance on currency being display-only or on interpreting real versus nominal returns. Baseline 3 is appropriate.

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 opens with a specific verb-plus-resource statement — calculating how long savings last at a given monthly withdrawal — and reinforces it with concrete phrasings an agent will actually encounter ("how long will $500k last", "will my money last to 90", "sabbatical runway"). The scope is clearly a depletion/runway calculation, which separates it from the retirement-age and FIRE-variant 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?

It gives explicit when-to-use triggers via many paraphrased user questions, then states explicit exclusions: annuity quotes, pension or Social Security payouts, tax on withdrawals, and investment selection. Both the positive and negative routing conditions are present, so an agent can decide without inference.

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