Untilfree - FIRE Calculator

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

Annotations cover only the safety profile (readOnly, idempotent, not destructive, closed-world), and the description adds real behavior beyond that: it returns the FIRE number under a 4% default, a date/days/age, a cautious-base-optimistic range and a year-by-year table, plus extra outputs when a purchase is supplied. It also discloses a notable interaction policy ('ask for any missing number instead of guessing') and an accuracy caveat ('An estimate, not financial advice').

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 primary use case, then return values, then exclusions, so an agent can stop reading early. It is dense but slightly overstuffed: the multi-country parenthetical ('also retire early in the UK, Canada or Australia') and the example lists (car, phone, holiday) add length without adding routing signal.

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 must describe returns, and it does: FIRE number, date and days left, age, a three-scenario range, a year-by-year table, and the purchase-specific deltas. Combined with coverage of the nested purchase object and the missing-input behavior, an agent has everything needed to call and interpret this correctly.

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 and the schema already carries parameter meaning. The description goes further by explaining what the optional nested purchase object actually changes in the output (days the date moves, what the money would grow to if invested instead) and that the withdrawal rate is adjustable, which is semantic guidance the schema does not phrase.

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 (calculate the FIRE number / financial independence date) and lists the exact user phrasings it answers ('when can I retire', 'FIRE number', 'how long until work is optional'). It also names the sibling it is not (retire_at_age), so the agent can separate it from alternatives without opening either 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?

Gives explicit when-to-use triggers (retirement date, FIRE number, purchase opportunity cost) and an explicit exclusion list: single-retirement-age questions route to retire_at_age, and products, loans, stock picks, tax, pension rules and live market data are all out of scope. The alternative is named rather than left to inference.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description adds genuinely useful framing beyond that: it states results are estimates and not financial advice, and it spells out computed defaults (fat at 150% of spending, lean at 75%) and the required inputs. It does not describe the shape of the returned numbers, which is the main residual gap.

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?

Sentences are front-loaded and each variant clause earns its place by encoding a distinct routing rule. There is mild keyword redundancy ('coast FIRE calculator, barista FIRE calculator or FIRE number calculator') that could be trimmed without losing 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?

For an 11-parameter calculator with no output schema, the description supplies what the agent most needs: required inputs, defaults for the optional ones, per-variant intent, and the estimate/not-advice caveat. It stops short of saying what the response contains (per-variant numbers, currency display), leaving a small gap for a multi-output calculator.

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 all 11 parameters including enums, defaults and bounds are already documented. The description only restates the required inputs and the optional monthly investing and target age, without adding format or interaction details beyond the schema — the baseline 3 applies.

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 names a concrete deliverable (a FIRE number for lean, fat, coast or barista variants) and ties each variant to the user's intent. It also explicitly contrasts itself with the sibling retire_at_age, so an agent can route without opening either 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?

It gives per-variant activation cues ('Use coast when...', 'Use barista when...', 'Use lean when...', 'Use fat when...') plus explicit exclusions (retire-at-age checks, job/salary advice, tax, investment picking) and names the alternative tool. This is the full when/when-not/alternatives pattern.

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

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.

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

Annotations already declare a read-only, idempotent, non-destructive computation, and the description goes further by disclosing how the output changes with input: baseline amount needed plus 4%/3.5%/3.3% withdrawal-rate variants, and with optional inputs added, the age reached, shortfall or surplus, and extra monthly amount required. It also sets the expectation that results are an estimate, not financial advice, which is useful framing for how an agent should present the numbers.

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?

It is front-loaded with the usage trigger and then moves to inputs and output behavior in a logical order. The long list of example phrasings is slightly dense but each cluster maps to a real query pattern, so little is wasted.

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 and nine parameters, the description carries the burden of explaining results and does so for both the minimal and enriched invocation modes. Combined with the currency coverage note and the scope exclusions, an agent has everything needed to call it and interpret the answer.

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 per-field meaning is already documented and the baseline is 3. The description adds cross-parameter semantics the schema cannot: spending must be monthly or yearly, target age is mandatory, and age/netWorth/monthlyInvestment are optional but unlock additional computed outputs, which tells the agent how to decide whether to supply them.

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 names a specific tool type (retirement calculator) scoped to a chosen target age and anchors it with concrete user phrasings like "can I retire at 50 with $500k" and "the 25x rule / 4% rule". It also explicitly distinguishes itself from calculate_freedom_day for the open-ended age question, so an agent can route correctly without opening either 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?

It gives explicit when-to-use triggers (age-specific retirement questions, 4%/25x rule) and explicit when-not-to-use cases (open "when can I retire" with no age, pension/Social Security/annuity rules, tax, investment selection), naming the alternative tool for the excluded case. Nothing is left to inference.

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