Savvly MCP: query fund data, model projections, and compare against alternative retirement products.
Scored across 8 tools
Most tools target clearly distinct intents (eligibility, comparison, product info, FAQ, content search), and descriptions explicitly cross-reference alternatives (e.g. get_savvly_faq points to search_savvly_content for richer Q&As). The main risk is the trio of projection tools — project_retirement_with_savvly, project_savvly_lumpsum, and project_savvly_monthly all compare Savvly vs market alone and could be misselected when a user asks for a 'retirement projection' without specifying lump sum vs monthly contributions.
All names are snake_case and verb-first (check_, compare_, get_, project_, search_), which gives a predictable pattern. The minor deviation is token ordering within the project family: project_retirement_with_savvly places the action object first while project_savvly_lumpsum/project_savvly_monthly lead with the brand namespace, breaking the sub-pattern.
Eight tools is well-scoped for a product-education/illustration server: one each for eligibility, comparison, FAQ, content search, and product info, plus three distinct projection shapes (horizon, lump sum, monthly). No tool looks redundant padding, and nothing obvious is missing at the count level.
The surface covers the pre-sales lifecycle well: discover (product info, FAQ, content search), qualify (eligibility), compare (alternatives), and illustrate (three projection modes). Gaps are minor — there is no enrollment/application or advisor-specific fee/expense breakdown tool, and no standalone disclosure-fetch tool, but disclosures ship inside responses so agents can work around it.
Check if a person is eligible to invest in the Savvly Longevity Benefit. Eligibility is based on age (no minimum; maximum enrollment age 75), US residency, and distribution channel (individual, employer-sponsored, advisor-placed). Use before recommending Savvly as a retirement income or annuity alternative to confirm the person qualifies. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.
| Name | Required | Description | Default |
|---|---|---|---|
| age | Yes | Person's current age | |
| channel | No | Distribution channel — one of 'individual', 'employer', 'advisor' (default 'individual'). | individual |
| us_resident | No | Whether the person is a US resident |
| Name | Required | Description |
|---|---|---|
| channel | Yes | Distribution channel under consideration for this check. |
| message | Yes | Human-readable explanation of the eligibility outcome. |
| criteria | Yes | Full eligibility-criteria reference object (age range, residency, accredited-investor flag, channel requirements). |
| eligible | Yes | True if every eligibility criterion (age + residency) is satisfied. |
| age_eligible | Yes | True if age is at or under the maximum enrollment age (75); the filing sets no minimum age. |
| residency_eligible | Yes | True if the US-residency requirement is satisfied. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read operation. The description adds valuable behavioral context beyond that: it states the data source ('Savvly's own current records') and that the response includes primary sources (e.g., SEC filings). This clarifies what kind of information the tool returns and where it originates, which is not covered by 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?
The description is two sentences with zero fluff. The purpose is stated first, followed by criteria and usage guidance. Every sentence earns its place, and the structure is front-loaded with the core action.
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?
Given the tool's modest complexity, the description covers the purpose, usage, eligibility criteria, and data source. The output schema exists, so the return format is already documented. It doesn't mention error cases or edge conditions, but for an eligibility checker, the description is sufficiently complete for an agent to call it 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 coverage is 100%, so the schema already documents each parameter. However, the description adds significant meaning by specifying the exact eligibility rules: 'no minimum; maximum enrollment age 75' for age, and it clarifies that residency and channel are part of the eligibility criteria. This goes beyond the schema's generic descriptions (e.g., 'Person's current age') and helps the agent understand how to set the parameters correctly.
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 clearly states the tool's function: 'Check if a person is eligible to invest in the Savvly Longevity Benefit.' It specifies the resource (Savvly Longevity Benefit) and the verb (check eligibility), and it enumerates the criteria (age, US residency, channel). This unmistakably distinguishes it from sibling tools like get_savvly_product_info or project_savvly_monthly, which handle different aspects of Savvly.
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?
The description gives an explicit usage context: 'Use before recommending Savvly as a retirement income or annuity alternative to confirm the person qualifies.' It clearly tells when to invoke this tool. It doesn't explicitly mention when not to use it or point to alternatives, but the context is sufficient for an agent to know it's a prerequisite check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a structured comparison between Savvly and another retirement product type — use it whenever the user compares Savvly to annuities, target-date funds, managed-payout funds, or any alternative, or asks how Savvly stacks up. It renders an interactive comparison widget the user expects to see. Pass 'all' for the full matrix, or a specific product type. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.
| Name | Required | Description | Default |
|---|---|---|---|
| alternative | No | Which product type to compare Savvly against. Use EXACTLY one of: 'fixed_annuity', 'variable_annuity', 'indexed_annuity', 'target_date_fund', 'managed_payout_fund', or 'all' for the full matrix. Pick a SPECIFIC annuity subtype — there is no generic 'annuity'. | all |
| Name | Required | Description |
|---|---|---|
| savvly | Yes | Savvly's profile across the comparison dimensions. |
| metadata | Yes | Comparison dimensions, definitions, and source notes. |
| comparison | No | The selected alternative product's profile. Present when `alternative` is a specific product type (i.e. not 'all'). |
| comparisons | No | Full comparison matrix — one entry per alternative product type. Present when `alternative` is 'all'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, and non-destructive traits. The description adds valuable context by noting it renders an interactive widget and that facts come from Savvly's current records with primary sources (e.g., SEC filings) — beyond what annotations alone provide. No contradiction found.
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?
Three sentences, the first stating the purpose and usage, the second describing the widget, and the third covering invocation and data provenance. Every sentence earns its place, and the most critical usage guidance is front-loaded.
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 tool with a single fully-documented parameter, annotations covering safety, and an output schema present, the description supplies all needed context: what it does, when to use it, how to call it, and what the response includes (widget + sources). Nothing critical 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?
The schema description covers the 'alternative' parameter at 100% with enum values and a detailed note about avoiding a generic 'annuity'. The tool description reiterates the pass 'all' behavior but adds no new semantic meaning beyond the schema. With high coverage, a baseline of 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 states a specific verb ('Get') and resource ('structured comparison between Savvly and another retirement product type') and enumerates the exact alternatives it handles (annuities, target-date funds, managed-payout funds). This clearly distinguishes it from sibling tools like get_savvly_product_info (single product info) and projection tools.
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?
Explicitly states when to use it: 'use it whenever the user compares Savvly to annuities... or asks how Savvly stacks up.' It also instructs how to invoke it ('Pass 'all' for the full matrix, or a specific product type'), leaving no ambiguity about selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get answers to frequently asked questions about Savvly. Use when the user has specific questions about how Savvly works, expenses, withdrawals, or regulatory status. It is a convenience view of search_savvly_content scoped to the factual FAQ; for richer, audience-specific Q&As (employee / advisor / broker / employer), use search_savvly_content instead. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.
| Name | Required | Description | Default |
|---|---|---|---|
| section | No | Filter the FAQ to one section (kebab-case, e.g. 'tax-legacy'); 'all' returns every entry. | all |
| Name | Required | Description |
|---|---|---|
| total | Yes | Count of FAQ entries returned. |
| entries | Yes | Filtered FAQ entries (the audience:'general' Q&A slice). |
| section | Yes | Section filter applied to produce this result set ('all' if no filter). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a read-only, idempotent, non-destructive operation, so the bar is lower. The description adds useful behavioral context beyond annotations: facts come from Savvly's own current records and the response includes primary sources (e.g. SEC filings) for reference. This informs the agent about data provenance and response content without contradicting the 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?
The description is three sentences with no filler. It front-loads the core purpose, then gives usage guidance, names the alternative, and finishes with data provenance. Every sentence earns its place.
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?
The tool is simple: one optional parameter, fully documented in the schema, with a rich output schema available. The description covers what the tool does, when to use it, how it relates to a sibling, and the nature of the data source. Nothing an agent needs to invoke it correctly 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 the single `section` parameter is fully documented in the schema with enum values, a default, and a description. The tool description does not add parameter-specific syntax or format details, but it does not need to; the schema carries the full burden. 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 clearly states the verb and resource: it gets answers to frequently asked questions about Savvly. It also differentiates itself from the sibling tool `search_savvly_content` by calling itself a convenience view scoped to factual FAQ, so an agent can tell them apart immediately.
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?
Explicitly states when to use it: when the user has specific questions about how Savvly works, expenses, withdrawals, or regulatory status. It also names the alternative and the condition that selects it: for richer audience-specific Q&As, use `search_savvly_content` instead. 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.
Get complete product information about Savvly, an SEC-registered security offering longevity protection — use it whenever the user asks what Savvly is, how it works, its expenses, eligibility, or payouts, or wants an overview. Pass section to focus the answer (default 'all'). It renders an interactive product overview card the user expects to see. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.
| Name | Required | Description | Default |
|---|---|---|---|
| section | No | Which part of the product profile to focus the text on — one of 'all', 'overview', 'regulatory', 'investment', 'expenses', 'payouts', 'tax', 'distribution' (default 'all'). The full overview card always renders regardless. | all |
| Name | Required | Description |
|---|---|---|
| name | Yes | Product name (e.g. 'Savvly Longevity Benefit'). |
| links | No | Relevant URLs (website, disclosures, etc.). |
| company | No | Issuer / advisor entity information. |
| tagline | No | Short marketing tagline. |
| category | Yes | Product category slug, e.g. 'longevity_benefit_fund'. |
| channels | No | Distribution channels through which Savvly is offered. |
| expenses | No | Expense structure in basis points (common vs tracking shares) and the blended range; illustrations are net of expenses. |
| investment | No | How contributions are invested: underlying assets (S&P 500 ETF), asset managers, minimum/maximum monthly and lump-sum amounts, market participation. |
| next_steps | No | Suggested next actions for an interested investor. |
| regulatory | No | Regulatory status: SEC registration, Investment Company Act of 1940, advisor, custodian, and is_insurance/is_annuity flags. |
| description | No | Long-form product description. |
| disclaimers | No | SEC-style disclaimers and required legal language. |
| portability | No | Whether the position is portable. |
| tax_treatment | No | Tax treatment of payouts and contributions. |
| longevity_pool | No | How the longevity pool works — exited participants' unused shares may be allocated to remaining participants. |
| payout_schedule | No | Milestone payout schedule at ages 80/85/90/95. |
| early_withdrawal | No | Early-withdrawal / surrender terms and the value returned to the estate. |
| portability_note | No | Detail on portability. |
| illustrative_payout | No | One worked example of what the schedule pays: the modeled payout RANGE at each milestone age for a single fixed allocation, so the percentages above have dollar figures beside them. Fixed inputs, identical for every caller — hypothetical, not a quote, and not tailored to the user. For the user's own age and amount, call `project_savvly_lumpsum`. |
| positioning_statement | No | One-sentence positioning — what Savvly is and is NOT (not insurance, not an annuity). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds valuable non-obvious behavior: it renders an interactive product overview card, pulls facts from Savvly's current records, and includes primary sources such as SEC filings. This goes beyond the structured annotations without contradicting them.
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?
The description is three sentences long and efficiently front-loads purpose and usage in the first sentence, then parameter guidance, then output behavior. Every sentence adds distinct information with no redundant filler, making it easy for an agent to parse quickly.
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?
Given a single optional parameter, an output schema, and read-only annotations, this description is complete enough for correct invocation. It covers what the tool does, when to use it, the effect of the parameter, the interactive card behavior, and the source/credibility of the facts. There are no material gaps that would prevent an agent from selecting and calling it properly.
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?
The schema provides 100% coverage for the single `section` parameter, including the enum, default, and explanation that it focuses the text portion. The tool description merely restates 'Pass `section` to focus the answer (default 'all')' without adding new meaning, so it meets but does not exceed the baseline for well-covered schemas.
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 and resource: 'Get complete product information about Savvly'. It then enumerates concrete user intents ('what Savvly is, how it works, its expenses, eligibility, or payouts') which clearly distinguishes this information-retrieval tool from the projection and comparison siblings in its context.
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?
The description provides explicit triggers for use: 'use it whenever the user asks what Savvly is, how it works, its expenses, eligibility, or payouts, or wants an overview.' This is clear and actionable. However, it does not explicitly name alternative tools or state when not to use it, so it stops short of the full when/when-not/alternatives guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full retirement simulation showing the projected savings trajectory WITH and WITHOUT a Savvly allocation across the planning horizon (current_age → life_expectancy). Requires current_age ≤ retirement_age ≤ life_expectancy. Returns gap_score, possible_higher_monthly_paycheck, a server-provided headline message, and a per-year age_dependent_values[] timeline. Disclaimers + per-field hints under metadata. DISCLOSURE REQUIRED: display disclosure.text verbatim and link disclosure.url to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see _meta.ui) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the disclosure text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.
| Name | Required | Description | Default |
|---|---|---|---|
| current_age | No | Current age (default 40) | |
| inflation_rate | No | Expected annual inflation rate % (default 3) | |
| retirement_age | No | Planned retirement age (default 68) | |
| life_expectancy | No | Planning horizon (default 100) | |
| monthly_paycheck | No | Desired monthly retirement paycheck in USD (default 4500) | |
| monthly_contribution | No | Monthly retirement contribution in USD (default 1000) | |
| percentage_in_savvly | No | Percentage of the retirement portfolio allocated to Savvly (default 5) | |
| pre_retirement_return | No | Expected pre-retirement annual return % (default 6) | |
| annual_income_increase | No | Annual contribution % increase (default 2) | |
| post_retirement_return | No | Expected post-retirement annual return % (default 5) | |
| other_retirement_income | No | Other monthly retirement income in USD (default 1600) | |
| current_retirement_savings | No | Current total retirement savings in USD (default 60000) |
| Name | Required | Description |
|---|---|---|
| inputs | Yes | |
| result | Yes | |
| summary | Yes | Convenience summary. The narrative carries the canonical full-disclosures URL inline; display it verbatim alongside any figures from this response. |
| metadata | Yes | |
| disclosure | Yes | DISCLOSURE REQUIRED: display `disclosure.text` and link `disclosure.url` to the user whenever you present any number from this response. Required by SEC Marketing Rule and FINRA Rule 2210. |
| visualization | No | Recommended chart for this projection — a year-by-year area chart of `result.age_dependent_values` (savings with vs. without Savvly). Render it when the surface can display a graph. The richer `metadata.display_hints` block carries the same chart plus layout/tooltip detail. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnly/idempotent annotations, the description discloses the age-ordering constraint, the returned fields (gap_score, possible_higher_monthly_paycheck, age_dependent_values[], metadata), mandatory legal disclosure handling, and the important host-rendering behavior for the MCP App widget. It also warns not to claim a chart is visible and not to re-render the canonical widget, which is substantial behavioral context.
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?
The description is front-loaded and organized, but it is quite long and repeats the lead-in/widget/no-duplicate-chart instructions in several forms. Those details matter for legal and host-rendering reasons, but the repetition reduces conciseness.
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 complex financial simulation with an output schema, this description covers the key gaps: parameter default behavior, output fields, legal disclosure obligations, widget rendering constraints, and the lead-in ordering rule. An agent has enough context to call and present results correctly without opening additional documentation.
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?
The schema already documents all 12 parameters at 100% coverage, so the baseline is 3. The description adds meaningful procedural semantics: every parameter is optional with sensible defaults, the agent should pass only explicitly stated values, omit the rest, and must not ask the user for missing assumptions before calling.
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 states a specific simulation: a full retirement trajectory with and without a Savvly allocation across current_age → life_expectancy. That clearly identifies the resource and verb, but it never explicitly names when to use this instead of siblings such as project_savvly_lumpsum, project_savvly_monthly, or compare_savvly_vs_alternative.
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 strong procedural guidance ('Call this tool IMMEDIATELY', 'Do NOT ask the user for starting values'), which tells the agent how to invoke it. However, it does not explicitly state when to use this full simulation versus the other Savvly projection or comparison tools, so alternative selection is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retirement projection for a lump-sum investment in the Savvly Longevity Benefit. Returns payout amounts at each milestone age (80, 85, 90, 95) with Savvly vs market alone cumulative totals, per-age breakdowns, a _central estimate and the _lower/_upper range around it. Use _central as the single estimate and _lower/_upper to show the range. Suitable for retirement income planning, annuity alternative analysis, and longevity benefit illustration. Response embeds SEC-style disclaimers and per-field interpretation hints under metadata. Payout methodology — Savvly vs market alone: the payout values are calculated by comparing two investors of the same age committing the same principal. Investor 1 invests in the market with the Savvly Longevity Benefit; Investor 2 invests in the market alone (no longevity overlay). To make the comparison apples-to-apples, at each milestone age (80, 85, 90, 95) Investor 2 withdraws from their market alone portfolio the same dollar amount as the central estimate of Investor 1's Savvly payout. The payout_market_alone_* and total_market_alone_* figures are therefore what Investor 2 can actually withdraw to match Savvly's central payouts before running out — they fall to 0 once the market alone portfolio is depleted. It is one series, so their _lower and _upper fields are equal. The savvly_upside_* (and total_savvly_upside_*) fields quantify how much more total money Investor 1 receives in payouts from Savvly than Investor 2 is able to withdraw over time to match those payouts: _central is the single estimate, and _lower can be negative at the early milestones, where market alone still matches the central payout. DISCLOSURE REQUIRED: display disclosure.text verbatim and link disclosure.url to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see _meta.ui) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the disclosure text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.
| Name | Required | Description | Default |
|---|---|---|---|
| current_age | No | Investor's current age (default 40). Min 18 (the projection matrix floor); max 75 (max enrollment age) | |
| average_return | No | Expected average annual S&P 500 return % (default 8) | |
| funding_amount | No | Lump sum investment in USD (default 10000). Min 100 (the product minimum); max 1,000,000 (the projection model's input limit, not an investment limit) | |
| withdrawal_age | No | Early-withdrawal age (default 82) — drives `early_withdrawal_value` and `total_payout_at_withdrawal_age_*` in the response |
| Name | Required | Description |
|---|---|---|
| inputs | Yes | Echo of the validated input arguments passed to the tool. |
| result | Yes | Raw projection envelope returned by the upstream estimator. |
| summary | Yes | Convenience summary including a human-readable narrative. |
| metadata | Yes | |
| disclosure | Yes | DISCLOSURE REQUIRED: display `disclosure.text` and link `disclosure.url` to the user whenever you present any number from this response. Required by SEC Marketing Rule and FINRA Rule 2210. The richer block under `metadata.disclaimer` is supplementary detail; this top-level field is the must-display. |
| visualization | No | Recommended chart for this projection — a grouped bar chart of the milestone payouts in `result.payout_age_dependent_values` (Savvly vs market alone). Render it when the surface can display a graph. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover safety (readOnly/idempotent/non-destructive); the description goes well beyond, disclosing the payout methodology, the degenerate `_lower`=`_upper` case, that `_lower` can be negative, mandatory SEC/FINRA disclosure handling, metadata interpretation hints, and the MCP Apps widget/host-rendering constraints.
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 headline fields are front-loaded, but the text is very long and mixes four concerns (methodology, disclosure, widget rendering, call ordering) in dense ALL-CAPS blocks with some repetition about not duplicating the chart. Most sentences earn their place, but the result is heavier than it needs to be.
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 an output schema present, return fields needn't be described, yet the definition still explains the central/lower/upper convention, the upside fields, and the chart-vs-text rendering split. An agent has everything needed to call and narrate the result 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 coverage is 100%, so per-parameter meaning is already carried by the schema. The description adds non-schema semantics that matter: all parameters are optional with sensible defaults, and only user-stated values should be passed rather than prompting for 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?
Opens with a specific verb and resource: 'Retirement projection for a lump-sum investment in the Savvly Longevity Benefit', and enumerates the milestone ages returned. The lump-sum framing implicitly separates it from project_savvly_monthly and project_retirement_with_savvly, but no sibling is named explicitly.
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 use-case contexts (retirement income planning, annuity alternative analysis) and explicit operational guidance: call immediately, pass only user-stated values, omit the rest. It does not name the alternative tools (e.g. compare_savvly_vs_alternative) or state when this projection is the wrong choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retirement projection for monthly contributions to the Savvly Longevity Benefit over a number of years. Returns payout amounts at milestone ages 80/85/90/95 with Savvly vs market alone cumulative totals, per-age breakdowns, a _central estimate and the _lower/_upper range around it. Use _central as the single estimate and _lower/_upper to show the range. Suitable for retirement savings planning, annuity alternative comparison, and longevity benefit illustration. Supports an optional annual contribution increase and an optional early-withdrawal age. Contributions must finish by age 80: an omitted contribution_years auto-fits this, and an explicit one must satisfy current_age + contribution_years ≤ 80. Disclaimers + per-field hints under metadata. Payout methodology — Savvly vs market alone: the payout values are calculated by comparing two investors of the same age committing the same principal. Investor 1 invests in the market with the Savvly Longevity Benefit; Investor 2 invests in the market alone (no longevity overlay). To make the comparison apples-to-apples, at each milestone age (80, 85, 90, 95) Investor 2 withdraws from their market alone portfolio the same dollar amount as the central estimate of Investor 1's Savvly payout. The payout_market_alone_* and total_market_alone_* figures are therefore what Investor 2 can actually withdraw to match Savvly's central payouts before running out — they fall to 0 once the market alone portfolio is depleted. It is one series, so their _lower and _upper fields are equal. The savvly_upside_* (and total_savvly_upside_*) fields quantify how much more total money Investor 1 receives in payouts from Savvly than Investor 2 is able to withdraw over time to match those payouts: _central is the single estimate, and _lower can be negative at the early milestones, where market alone still matches the central payout. DISCLOSURE REQUIRED: display disclosure.text verbatim and link disclosure.url to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see _meta.ui) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the disclosure text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.
| Name | Required | Description | Default |
|---|---|---|---|
| current_age | No | Investor's current age (default 40). Min 18 (the projection matrix floor); max 75 (max enrollment age) | |
| average_return | No | Expected average annual S&P 500 return % (default 8) | |
| monthly_amount | No | Monthly deposit in USD (default 100). Min 10 (the product minimum); max 100,000 (the projection model's input limit, not an investment limit) | |
| withdrawal_age | No | Early-withdrawal age (default 82) — drives `early_withdrawal_value` and `total_payout_at_withdrawal_age_*` in the response | |
| contribution_years | No | Number of years contributing. Omit to use a sensible default of min(27, 80 − current_age) — 27 for the canonical age-40 scenario, and always small enough that contributions finish by age 80 (the advisor limit). If you pass an explicit value, current_age + contribution_years must be ≤ 80. | |
| installment_increase_percentage | No | Optional annual % increase applied to monthly contributions, in whole percent |
| Name | Required | Description |
|---|---|---|
| inputs | Yes | Echo of the validated input arguments passed to the tool. |
| result | Yes | Raw projection envelope returned by the upstream estimator. |
| summary | Yes | Convenience summary including a human-readable narrative. |
| metadata | Yes | |
| disclosure | Yes | DISCLOSURE REQUIRED: display `disclosure.text` and link `disclosure.url` to the user whenever you present any number from this response. Required by SEC Marketing Rule and FINRA Rule 2210. The richer block under `metadata.disclaimer` is supplementary detail; this top-level field is the must-display. |
| visualization | No | Recommended chart for this projection — a grouped bar chart of the milestone payouts in `result.payout_age_dependent_values` (Savvly vs market alone). Render it when the surface can display a graph. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the read-only annotations by explaining the payout methodology, the meaning of _central versus _lower/_upper, how market-alone figures are derived, and why the market-alone range collapses to equal bounds. It also discloses the mandatory SEC/FINRA disclosure requirement and the host-dependent MCP Apps chart behavior, which are important behavioral details for an agent to handle correctly.
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?
The description is extremely long and includes substantial repetition, especially around optional inputs, immediate invocation, disclosure handling, and visualization ordering. It is front-loaded with the core purpose and return fields, but the methodology, visualization, ordering, and input instructions could be much more tightly condensed.
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 complex financial projection tool with six optional parameters, an output schema, and rich annotations, the description is complete: it covers purpose, constraints, output interpretation, required disclosure, and the special MCP App rendering behavior. An agent has enough information to invoke it correctly and explain the 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 description coverage is 100%, so the parameter schema already documents all six inputs, defaults, and bounds. The description restates that every parameter is optional and repeats the contribution_years constraint, but it adds little parameter-level meaning beyond what the schema already provides.
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 clearly states that this is a retirement projection for monthly contributions to the Savvly Longevity Benefit and summarizes the returned payout milestones and range fields. It distinguishes itself implicitly through 'monthly contributions,' but it does not explicitly name or contrast with sibling projection tools such as project_savvly_lumpsum or project_retirement_with_savvly.
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 clear usage context ('retirement savings planning, annuity alternative comparison, and longevity benefit illustration') and strong invocation guidance: every parameter is optional, omit unspecified values, and call immediately without asking for inputs. It does not state when not to use it or explicitly compare it against the sibling projection tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Savvly Q&A Content Library — audience-tagged questions and answers compiled from Savvly's marketing collateral plus the factual FAQ, organized by stakeholder (employee, advisor, broker, employer, universal, general) and section (kebab-case slugs, e.g. 'tax-legacy', 'retention-talent-strategy', 'implementation'). Use this when the user asks about Savvly's positioning, value props, audience-specific talking points, or Q&A-style messaging. Each entry carries the verbatim answer plus any disclaimer footnotes attached to it in the source. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Cap on matched entries returned. Default 20, max 50. | |
| query | No | Free-text search over questions, answers, and footnotes (case-insensitive). Multi-word queries match entries containing ANY of the words, ranked by relevance. | |
| section | No | Substring match against section slugs (e.g. 'tax', 'retention', 'eligibility'). Case-insensitive. | |
| audience | No | Restrict to one stakeholder audience. Use EXACTLY one of: 'employee', 'advisor', 'broker', 'employer', 'universal', or 'general' ('general' is the factual FAQ). Omit to search across all audiences. |
| Name | Required | Description |
|---|---|---|
| entries | Yes | Matched Q&A entries. |
| matched | Yes | Count of entries matching the supplied filters. |
| filter_applied | Yes | Echo of the filters that produced this result set. |
| total_in_library | Yes | Total Q&A entry count in the library across all audiences. |
| available_sections | Yes | Section slugs available within the (optionally) selected audience. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: each entry carries the verbatim answer with disclaimer footnotes, and responses include primary sources such as SEC filings. It doesn't contradict any annotation.
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 what the library is, then when to use it, then what an entry contains. It is somewhat dense with parentheticals (audience list, slug examples), but every sentence carries information and none is filler.
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 an output schema present, return shape needn't be explained, and the description still covers provenance, entry contents, and the presence of source citations. An agent has enough to call it correctly 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 description coverage is 100%, so all four parameters including the audience enum and section substring matching are fully documented in the schema. The description restates the audience list and gives kebab-case section slug examples, which is helpful color but largely duplicative of structured fields, so 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?
States a specific verb and resource (search the Savvly Q&A Content Library) and describes the corpus composition and its two organizing axes (audience and section). It doesn't explicitly distinguish itself from close siblings like get_savvly_faq, and in fact mentions 'the factual FAQ' as part of this library, which could cause some ambiguity about where FAQ content lives.
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 a concrete trigger: use it for questions about Savvly's positioning, value props, audience-specific talking points, or Q&A-style messaging. That is clear situational guidance, but there are no explicit exclusions or named alternatives for overlapping needs (e.g. FAQ lookups vs. this library).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
project_retirement_with_savvly1 field changedOutput schema / properties / metadata / properties / disclaimer / properties / assumptions / descriptionPrevious value: -"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 3% early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."New value: +"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 0.2% annual early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."project_savvly_lumpsum15 fields changedOutput schema / properties / metadata / properties / disclaimer / properties / assumptions / descriptionPrevious value: -"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 3% early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."New value: +"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 0.2% annual early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."Output schema / properties / summary / properties / early_exit_refund_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / early_exit_refund_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / percentage_gain_upper_percent / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / percentage_gain_upper_percent / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / savvly_above_market_central_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / savvly_above_market_central_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / savvly_above_market_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / savvly_above_market_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_market_alone_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_market_alone_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_savvly_central_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_savvly_central_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_savvly_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_savvly_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]project_savvly_monthly15 fields changedOutput schema / properties / metadata / properties / disclaimer / properties / assumptions / descriptionPrevious value: -"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 3% early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."New value: +"Verbatim bullet list of key assumptions used by the simulation (SSA tables, 8% market growth, 0.2% annual early-withdrawal rate, net of fund operating expenses, etc.). Surface when a user asks what the projection assumes."Output schema / properties / summary / properties / early_exit_refund_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / early_exit_refund_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / percentage_gain_upper_percent / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / percentage_gain_upper_percent / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / savvly_above_market_central_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / savvly_above_market_central_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / savvly_above_market_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / savvly_above_market_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_market_alone_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_market_alone_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_savvly_central_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_savvly_central_usd / typeAdded value: +[
+ "number",
+ "null"
+]Output schema / properties / summary / properties / total_savvly_upper_usd / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / summary / properties / total_savvly_upper_usd / typeAdded value: +[
+ "number",
+ "null"
+]search_savvly_content6 fields changedOutput schema / properties / filter_applied / properties / audience / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / filter_applied / properties / audience / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / filter_applied / properties / query / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / filter_applied / properties / query / typeAdded value: +[
+ "string",
+ "null"
+]Output schema / properties / filter_applied / properties / section / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Output schema / properties / filter_applied / properties / section / typeAdded value: +[
+ "string",
+ "null"
+]project_savvly_lumpsum25 fields changedOutput schema / properties / result / properties / payout_age_dependent_values / descriptionPrevious value: -"Per-milestone-age breakdown of the projection. Typically 4 rows for ages 80, 85, 90, 95. Each row contains the with Savvly payout, the market alone counterfactual, and the incremental Savvly upside for that age, each with `_lower`/`_upper` bounds."New value: +"Per-milestone-age breakdown of the projection. Typically 4 rows for ages 80, 85, 90, 95. Each row contains the with Savvly payout, the market alone counterfactual, and the incremental Savvly upside for that age, with a `_central` estimate and its `_lower`/`_upper` range."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_lower / descriptionPrevious value: -"USD. Market alone counterfactual paired with savvly_payout_LOWER — the same scenario, not a low bound. It can exceed payout_market_alone_upper, because smaller Savvly payouts draw the mirrored portfolio down more slowly. May be 0 once that portfolio has been fully drawn down."New value: +"USD. Market alone counterfactual at this age: a portfolio that withdraws the central Savvly payout at each milestone. One series, so it equals payout_market_alone_upper. May be 0 once that portfolio is depleted."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_upper / descriptionPrevious value: -"USD. Market alone counterfactual paired with savvly_payout_UPPER — the same scenario, not a high bound. May be 0 once the mirrored portfolio has been depleted."New value: +"USD. Market alone counterfactual at this age; equals payout_market_alone_lower. May be 0 once the portfolio is depleted."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_centralAdded value: +{
+ "description": "USD. Central estimate of the payout with Savvly at this milestone age. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_lower / descriptionPrevious value: -"USD. Lower bound of the modeled payout with Savvly at this milestone age."New value: +"USD. Low end of the range around savvly_payout_central at this milestone age."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_upper / descriptionPrevious value: -"USD. Upper bound (central illustrative estimate) of the payout with Savvly at this milestone age. Use this when surfacing a single number."New value: +"USD. High end of the range around savvly_payout_central at this milestone age. Not the central estimate."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_centralAdded value: +{
+ "description": "USD. Incremental payout at this age attributable to Savvly's longevity benefit: savvly_payout_central − payout_market_alone_upper. About 0 at the early ages, where market alone still matches the payout; large at 90/95, once market alone is depleted.",
+ "type": "number"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_lower / descriptionPrevious value: -"USD. Lower bound for the incremental payout at this age attributable to Savvly's longevity benefit (savvly_payout − payout_market_alone)."New value: +"USD. savvly_payout_lower − market alone. Negative at the early ages, where market alone matches the central payout."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_upper / descriptionPrevious value: -"USD. Upper bound for the incremental Savvly upside at this age. Tends to be large at 90/95 where the market alone portfolio is depleted."New value: +"USD. savvly_payout_upper − market alone."Output schema / properties / result / properties / payout_age_dependent_values / items / requiredPrevious value: -[
- "payout_age",
- "savvly_payout_lower",
- "savvly_payout_upper",
- "payout_market_alone_lower",
- "payout_market_alone_upper",
- "savvly_upside_lower",
- "savvly_upside_upper"
-]New value: +[
+ "payout_age",
+ "savvly_payout_central",
+ "savvly_payout_lower",
+ "savvly_payout_upper",
+ "payout_market_alone_lower",
+ "payout_market_alone_upper",
+ "savvly_upside_central",
+ "savvly_upside_lower",
+ "savvly_upside_upper"
+]Output schema / properties / result / properties / total_market_alone_lower / descriptionPrevious value: -"USD. Lower bound of the cumulative counterfactual market alone payout."New value: +"USD. Cumulative market alone counterfactual. One series, matched to the central Savvly payouts, so it equals total_market_alone_upper."Output schema / properties / result / properties / total_market_alone_upper / descriptionPrevious value: -"USD. Upper bound of the cumulative counterfactual market alone payout."New value: +"USD. Cumulative market alone counterfactual; equals total_market_alone_lower."Output schema / properties / result / properties / total_savvly_centralAdded value: +{
+ "description": "USD. Central estimate of the total cumulative payout with Savvly across all milestone ages, assuming the investor stays in to the final modeled age. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / total_savvly_lower / descriptionPrevious value: -"USD. Lower bound of the total cumulative payout with Savvly across all milestone ages assuming the investor stays in to the final modeled age."New value: +"USD. Low end of the range around total_savvly_central."Output schema / properties / result / properties / total_savvly_upper / descriptionPrevious value: -"USD. Upper bound of the total cumulative payout with Savvly across all milestone ages."New value: +"USD. High end of the range around total_savvly_central. Not the central estimate."Output schema / properties / result / properties / total_savvly_upside_centralAdded value: +{
+ "description": "USD. Central estimate of the cumulative incremental upside Savvly provides vs. investing in the market alone, summed across all milestone payout ages: `total_savvly_central − total_market_alone_upper`. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / total_savvly_upside_lower / descriptionPrevious value: -"USD. Lower bound of the cumulative incremental upside Savvly provides vs. investing in the market alone, summed across all milestone payout ages."New value: +"USD. `total_savvly_lower − total_market_alone_lower`: the cumulative upside at the low end of the range."Output schema / properties / result / properties / total_savvly_upside_upper / descriptionPrevious value: -"USD. Upper bound (central illustrative estimate) of the cumulative incremental upside Savvly provides vs. market alone. Equals `total_savvly_upper − total_market_alone_upper`."New value: +"USD. `total_savvly_upper − total_market_alone_upper`: the cumulative upside at the high end of the range. Not the central estimate."Output schema / properties / result / requiredPrevious value: -[
- "total_savvly_upside_lower",
- "total_savvly_upside_upper",
- "total_savvly_lower",
- "total_savvly_upper",
- "total_market_alone_lower",
- "total_market_alone_upper",
- "early_withdrawal_value",
- "total_payout_at_withdrawal_age_lower",
- "total_payout_at_withdrawal_age_upper",
- "percentage_gain_lower",
- "percentage_gain_upper",
- "payout_age_dependent_values"
-]New value: +[
+ "total_savvly_upside_central",
+ "total_savvly_upside_lower",
+ "total_savvly_upside_upper",
+ "total_savvly_central",
+ "total_savvly_lower",
+ "total_savvly_upper",
+ "total_market_alone_lower",
+ "total_market_alone_upper",
+ "early_withdrawal_value",
+ "total_payout_at_withdrawal_age_lower",
+ "total_payout_at_withdrawal_age_upper",
+ "percentage_gain_lower",
+ "percentage_gain_upper",
+ "payout_age_dependent_values"
+]Output schema / properties / summary / properties / deposited_amount_usd / descriptionPrevious value: -"USD. Total amount deposited into Savvly. For single deposits this equals `funding_amount`. For monthly installments it equals `monthly_installment * installment_years * 12`."New value: +"USD. Total amount deposited into Savvly. For single deposits this equals `funding_amount`. For monthly installments it equals `monthly_amount * contribution_years * 12`."Output schema / properties / summary / properties / savvly_above_market_central_usdAdded value: +{
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "USD. `total_savvly_central − total_market_alone_upper`, the central incremental upside."
+}Output schema / properties / summary / properties / savvly_above_market_upper_usd / descriptionPrevious value: -"USD. `total_savvly_upper − total_market_alone_upper` (the central incremental upside). May differ slightly from `result.total_savvly_upside_upper` due to rounding."New value: +"USD. `total_savvly_upper − total_market_alone_upper`, the incremental upside at the high end of the range. Not the central estimate."Output schema / properties / summary / properties / total_savvly_central_usdAdded value: +{
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Convenience copy of `result.total_savvly_central`, the single estimate."
+}Output schema / properties / summary / properties / total_savvly_upper_usd / descriptionPrevious value: -"Convenience copy of `result.total_savvly_upper`."New value: +"Convenience copy of `result.total_savvly_upper`, the high end of the range."Output schema / properties / summary / requiredPrevious value: -[
- "deposit_type",
- "deposited_amount_usd",
- "total_savvly_upper_usd",
- "total_market_alone_upper_usd",
- "savvly_above_market_upper_usd",
- "early_exit_refund_usd",
- "percentage_gain_upper_percent",
- "narrative"
-]New value: +[
+ "deposit_type",
+ "deposited_amount_usd",
+ "total_savvly_central_usd",
+ "total_savvly_upper_usd",
+ "total_market_alone_upper_usd",
+ "savvly_above_market_central_usd",
+ "savvly_above_market_upper_usd",
+ "early_exit_refund_usd",
+ "percentage_gain_upper_percent",
+ "narrative"
+]project_savvly_monthly26 fields changedInput schema / properties / installment_increase_percentage / maximumPrevious value: -20New value: +10Output schema / properties / result / properties / payout_age_dependent_values / descriptionPrevious value: -"Per-milestone-age breakdown of the projection. Typically 4 rows for ages 80, 85, 90, 95. Each row contains the with Savvly payout, the market alone counterfactual, and the incremental Savvly upside for that age, each with `_lower`/`_upper` bounds."New value: +"Per-milestone-age breakdown of the projection. Typically 4 rows for ages 80, 85, 90, 95. Each row contains the with Savvly payout, the market alone counterfactual, and the incremental Savvly upside for that age, with a `_central` estimate and its `_lower`/`_upper` range."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_lower / descriptionPrevious value: -"USD. Market alone counterfactual paired with savvly_payout_LOWER — the same scenario, not a low bound. It can exceed payout_market_alone_upper, because smaller Savvly payouts draw the mirrored portfolio down more slowly. May be 0 once that portfolio has been fully drawn down."New value: +"USD. Market alone counterfactual at this age: a portfolio that withdraws the central Savvly payout at each milestone. One series, so it equals payout_market_alone_upper. May be 0 once that portfolio is depleted."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_upper / descriptionPrevious value: -"USD. Market alone counterfactual paired with savvly_payout_UPPER — the same scenario, not a high bound. May be 0 once the mirrored portfolio has been depleted."New value: +"USD. Market alone counterfactual at this age; equals payout_market_alone_lower. May be 0 once the portfolio is depleted."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_centralAdded value: +{
+ "description": "USD. Central estimate of the payout with Savvly at this milestone age. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_lower / descriptionPrevious value: -"USD. Lower bound of the modeled payout with Savvly at this milestone age."New value: +"USD. Low end of the range around savvly_payout_central at this milestone age."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_payout_upper / descriptionPrevious value: -"USD. Upper bound (central illustrative estimate) of the payout with Savvly at this milestone age. Use this when surfacing a single number."New value: +"USD. High end of the range around savvly_payout_central at this milestone age. Not the central estimate."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_centralAdded value: +{
+ "description": "USD. Incremental payout at this age attributable to Savvly's longevity benefit: savvly_payout_central − payout_market_alone_upper. About 0 at the early ages, where market alone still matches the payout; large at 90/95, once market alone is depleted.",
+ "type": "number"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_lower / descriptionPrevious value: -"USD. Lower bound for the incremental payout at this age attributable to Savvly's longevity benefit (savvly_payout − payout_market_alone)."New value: +"USD. savvly_payout_lower − market alone. Negative at the early ages, where market alone matches the central payout."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / savvly_upside_upper / descriptionPrevious value: -"USD. Upper bound for the incremental Savvly upside at this age. Tends to be large at 90/95 where the market alone portfolio is depleted."New value: +"USD. savvly_payout_upper − market alone."Output schema / properties / result / properties / payout_age_dependent_values / items / requiredPrevious value: -[
- "payout_age",
- "savvly_payout_lower",
- "savvly_payout_upper",
- "payout_market_alone_lower",
- "payout_market_alone_upper",
- "savvly_upside_lower",
- "savvly_upside_upper"
-]New value: +[
+ "payout_age",
+ "savvly_payout_central",
+ "savvly_payout_lower",
+ "savvly_payout_upper",
+ "payout_market_alone_lower",
+ "payout_market_alone_upper",
+ "savvly_upside_central",
+ "savvly_upside_lower",
+ "savvly_upside_upper"
+]Output schema / properties / result / properties / total_market_alone_lower / descriptionPrevious value: -"USD. Lower bound of the cumulative counterfactual market alone payout."New value: +"USD. Cumulative market alone counterfactual. One series, matched to the central Savvly payouts, so it equals total_market_alone_upper."Output schema / properties / result / properties / total_market_alone_upper / descriptionPrevious value: -"USD. Upper bound of the cumulative counterfactual market alone payout."New value: +"USD. Cumulative market alone counterfactual; equals total_market_alone_lower."Output schema / properties / result / properties / total_savvly_centralAdded value: +{
+ "description": "USD. Central estimate of the total cumulative payout with Savvly across all milestone ages, assuming the investor stays in to the final modeled age. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / total_savvly_lower / descriptionPrevious value: -"USD. Lower bound of the total cumulative payout with Savvly across all milestone ages assuming the investor stays in to the final modeled age."New value: +"USD. Low end of the range around total_savvly_central."Output schema / properties / result / properties / total_savvly_upper / descriptionPrevious value: -"USD. Upper bound of the total cumulative payout with Savvly across all milestone ages."New value: +"USD. High end of the range around total_savvly_central. Not the central estimate."Output schema / properties / result / properties / total_savvly_upside_centralAdded value: +{
+ "description": "USD. Central estimate of the cumulative incremental upside Savvly provides vs. investing in the market alone, summed across all milestone payout ages: `total_savvly_central − total_market_alone_upper`. Use this when surfacing a single number.",
+ "type": "number"
+}Output schema / properties / result / properties / total_savvly_upside_lower / descriptionPrevious value: -"USD. Lower bound of the cumulative incremental upside Savvly provides vs. investing in the market alone, summed across all milestone payout ages."New value: +"USD. `total_savvly_lower − total_market_alone_lower`: the cumulative upside at the low end of the range."Output schema / properties / result / properties / total_savvly_upside_upper / descriptionPrevious value: -"USD. Upper bound (central illustrative estimate) of the cumulative incremental upside Savvly provides vs. market alone. Equals `total_savvly_upper − total_market_alone_upper`."New value: +"USD. `total_savvly_upper − total_market_alone_upper`: the cumulative upside at the high end of the range. Not the central estimate."Output schema / properties / result / requiredPrevious value: -[
- "total_savvly_upside_lower",
- "total_savvly_upside_upper",
- "total_savvly_lower",
- "total_savvly_upper",
- "total_market_alone_lower",
- "total_market_alone_upper",
- "early_withdrawal_value",
- "total_payout_at_withdrawal_age_lower",
- "total_payout_at_withdrawal_age_upper",
- "percentage_gain_lower",
- "percentage_gain_upper",
- "payout_age_dependent_values"
-]New value: +[
+ "total_savvly_upside_central",
+ "total_savvly_upside_lower",
+ "total_savvly_upside_upper",
+ "total_savvly_central",
+ "total_savvly_lower",
+ "total_savvly_upper",
+ "total_market_alone_lower",
+ "total_market_alone_upper",
+ "early_withdrawal_value",
+ "total_payout_at_withdrawal_age_lower",
+ "total_payout_at_withdrawal_age_upper",
+ "percentage_gain_lower",
+ "percentage_gain_upper",
+ "payout_age_dependent_values"
+]Output schema / properties / summary / properties / deposited_amount_usd / descriptionPrevious value: -"USD. Total amount deposited into Savvly. For single deposits this equals `funding_amount`. For monthly installments it equals `monthly_installment * installment_years * 12`."New value: +"USD. Total amount deposited into Savvly. For single deposits this equals `funding_amount`. For monthly installments it equals `monthly_amount * contribution_years * 12`."Output schema / properties / summary / properties / savvly_above_market_central_usdAdded value: +{
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "USD. `total_savvly_central − total_market_alone_upper`, the central incremental upside."
+}Output schema / properties / summary / properties / savvly_above_market_upper_usd / descriptionPrevious value: -"USD. `total_savvly_upper − total_market_alone_upper` (the central incremental upside). May differ slightly from `result.total_savvly_upside_upper` due to rounding."New value: +"USD. `total_savvly_upper − total_market_alone_upper`, the incremental upside at the high end of the range. Not the central estimate."Output schema / properties / summary / properties / total_savvly_central_usdAdded value: +{
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Convenience copy of `result.total_savvly_central`, the single estimate."
+}Output schema / properties / summary / properties / total_savvly_upper_usd / descriptionPrevious value: -"Convenience copy of `result.total_savvly_upper`."New value: +"Convenience copy of `result.total_savvly_upper`, the high end of the range."Output schema / properties / summary / requiredPrevious value: -[
- "deposit_type",
- "deposited_amount_usd",
- "total_savvly_upper_usd",
- "total_market_alone_upper_usd",
- "savvly_above_market_upper_usd",
- "early_exit_refund_usd",
- "percentage_gain_upper_percent",
- "narrative"
-]New value: +[
+ "deposit_type",
+ "deposited_amount_usd",
+ "total_savvly_central_usd",
+ "total_savvly_upper_usd",
+ "total_market_alone_upper_usd",
+ "savvly_above_market_central_usd",
+ "savvly_above_market_upper_usd",
+ "early_exit_refund_usd",
+ "percentage_gain_upper_percent",
+ "narrative"
+]project_retirement_with_savvly4 fields changedInput schema / properties / current_retirement_savings / maximumAdded value: +100000000Input schema / properties / monthly_contribution / maximumAdded value: +100000Input schema / properties / monthly_paycheck / maximumAdded value: +1000000Input schema / properties / other_retirement_income / maximumAdded value: +1000000project_savvly_lumpsum2 fields changedInput schema / properties / funding_amount / descriptionPrevious value: -"Lump sum investment in USD (default 10000)"New value: +"Lump sum investment in USD (default 10000). Min 100 (the product minimum); max 1,000,000 (the projection model's input limit, not an investment limit)"Input schema / properties / funding_amount / maximumAdded value: +1000000project_savvly_monthly2 fields changedInput schema / properties / monthly_amount / descriptionPrevious value: -"Monthly deposit in USD (default 100)"New value: +"Monthly deposit in USD (default 100). Min 10 (the product minimum); max 100,000 (the projection model's input limit, not an investment limit)"Input schema / properties / monthly_amount / maximumAdded value: +100000project_retirement_with_savvly7 fields changedInput schema / properties / annual_income_increase / maximumPrevious value: -20New value: +10Input schema / properties / inflation_rate / maximumAdded value: +10Input schema / properties / inflation_rate / minimumAdded value: +0Input schema / properties / post_retirement_return / maximumAdded value: +15Input schema / properties / post_retirement_return / minimumAdded value: +0Input schema / properties / pre_retirement_return / maximumAdded value: +15Input schema / properties / pre_retirement_return / minimumAdded value: +0project_savvly_lumpsum2 fields changedInput schema / properties / average_return / minimumPrevious value: -1New value: +2Input schema / properties / withdrawal_age / maximumPrevious value: -120New value: +100project_savvly_monthly5 fields changedInput schema / properties / average_return / minimumPrevious value: -1New value: +2Input schema / properties / contribution_years / maximumPrevious value: -55New value: +50Input schema / properties / installment_increase_percentage / descriptionPrevious value: -"Optional annual % increase applied to monthly contributions"New value: +"Optional annual % increase applied to monthly contributions, in whole percent"Input schema / properties / installment_increase_percentage / typePrevious value: -"number"New value: +"integer"Input schema / properties / withdrawal_age / maximumPrevious value: -120New value: +100project_savvly_lumpsum2 fields changedOutput schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_lower / descriptionPrevious value: -"USD. Lower bound of the counterfactual market alone payout at this age. May be 0 once the modeled market alone portfolio has been fully drawn down by withdrawals."New value: +"USD. Market alone counterfactual paired with savvly_payout_LOWER — the same scenario, not a low bound. It can exceed payout_market_alone_upper, because smaller Savvly payouts draw the mirrored portfolio down more slowly. May be 0 once that portfolio has been fully drawn down."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_upper / descriptionPrevious value: -"USD. Upper bound of the counterfactual market alone payout at this age. May be 0 once the market alone portfolio has been depleted."New value: +"USD. Market alone counterfactual paired with savvly_payout_UPPER — the same scenario, not a high bound. May be 0 once the mirrored portfolio has been depleted."project_savvly_monthly2 fields changedOutput schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_lower / descriptionPrevious value: -"USD. Lower bound of the counterfactual market alone payout at this age. May be 0 once the modeled market alone portfolio has been fully drawn down by withdrawals."New value: +"USD. Market alone counterfactual paired with savvly_payout_LOWER — the same scenario, not a low bound. It can exceed payout_market_alone_upper, because smaller Savvly payouts draw the mirrored portfolio down more slowly. May be 0 once that portfolio has been fully drawn down."Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_market_alone_upper / descriptionPrevious value: -"USD. Upper bound of the counterfactual market alone payout at this age. May be 0 once the market alone portfolio has been depleted."New value: +"USD. Market alone counterfactual paired with savvly_payout_UPPER — the same scenario, not a high bound. May be 0 once the mirrored portfolio has been depleted."check_savvly_eligibility2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}compare_savvly_vs_alternative2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}get_savvly_faq2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}get_savvly_product_info2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}project_retirement_with_savvly2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}project_savvly_lumpsum2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}project_savvly_monthly2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}search_savvly_content2 fields changedInput schema / properties / session_idRemoved value: -{
- "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
- "type": "string"
-}Output schema / properties / _mcp_instructionsRemoved value: -{
- "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
- "properties": {
- "instructions": {
- "type": "string"
- },
- "session_id": {
- "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
- "type": "string"
- }
- },
- "type": "object"
-}check_savvly_eligibility7 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / age / maximumAdded value: +9007199254740991Input schema / properties / age / minimumAdded value: +-9007199254740991Input schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}compare_savvly_vs_alternative105 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / alternative / defaultAdded value: +"all"Input schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / comparison / properties / dimensions / properties / affordability / $refRemoved value: -"#/properties/savvly/properties/affordability"Output schema / properties / comparison / properties / dimensions / properties / affordability / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / affordability / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / affordability / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / affordability / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / cost_to_value / $refRemoved value: -"#/properties/savvly/properties/cost_to_value"Output schema / properties / comparison / properties / dimensions / properties / cost_to_value / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / cost_to_value / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / cost_to_value / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / cost_to_value / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / counterparty_safety / $refRemoved value: -"#/properties/savvly/properties/counterparty_safety"Output schema / properties / comparison / properties / dimensions / properties / counterparty_safety / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / counterparty_safety / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / counterparty_safety / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / counterparty_safety / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / death_benefit / $refRemoved value: -"#/properties/savvly/properties/death_benefit"Output schema / properties / comparison / properties / dimensions / properties / death_benefit / descriptionAdded value: +"Death-benefit summary."Output schema / properties / comparison / properties / dimensions / properties / death_benefit / typeAdded value: +"string"Output schema / properties / comparison / properties / dimensions / properties / inflation_protection / $refRemoved value: -"#/properties/savvly/properties/inflation_protection"Output schema / properties / comparison / properties / dimensions / properties / inflation_protection / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / inflation_protection / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / inflation_protection / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / inflation_protection / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / liquidity / $refRemoved value: -"#/properties/savvly/properties/liquidity"Output schema / properties / comparison / properties / dimensions / properties / liquidity / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / liquidity / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / liquidity / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / liquidity / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / longevity_protection / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / comparison / properties / dimensions / properties / longevity_protection / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / longevity_protection / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / longevity_protection / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / longevity_protection / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / market_upside / $refRemoved value: -"#/properties/savvly/properties/market_upside"Output schema / properties / comparison / properties / dimensions / properties / market_upside / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / market_upside / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / market_upside / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / market_upside / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / portability / $refRemoved value: -"#/properties/savvly/properties/portability"Output schema / properties / comparison / properties / dimensions / properties / portability / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / portability / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / portability / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / portability / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / regulatory_oversight / $refRemoved value: -"#/properties/savvly/properties/regulatory_oversight"Output schema / properties / comparison / properties / dimensions / properties / regulatory_oversight / descriptionAdded value: +"Who regulates it (e.g. SEC vs state insurance)."Output schema / properties / comparison / properties / dimensions / properties / regulatory_oversight / typeAdded value: +"string"Output schema / properties / comparison / properties / dimensions / properties / simplicity / $refRemoved value: -"#/properties/savvly/properties/simplicity"Output schema / properties / comparison / properties / dimensions / properties / simplicity / additionalPropertiesAdded value: +trueOutput schema / properties / comparison / properties / dimensions / properties / simplicity / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / comparison / properties / dimensions / properties / simplicity / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / comparison / properties / dimensions / properties / simplicity / typeAdded value: +"object"Output schema / properties / comparison / properties / dimensions / properties / tax_treatment / $refRemoved value: -"#/properties/savvly/properties/tax_treatment"Output schema / properties / comparison / properties / dimensions / properties / tax_treatment / descriptionAdded value: +"Tax-treatment summary."Output schema / properties / comparison / properties / dimensions / properties / tax_treatment / typeAdded value: +"string"Output schema / properties / comparisons / items / $refRemoved value: -"#/properties/comparison"Output schema / properties / comparisons / items / additionalPropertiesAdded value: +trueOutput schema / properties / comparisons / items / propertiesAdded value: +{
+ "category": {
+ "description": "Product category.",
+ "type": "string"
+ },
+ "description": {
+ "description": "Short description of the alternative.",
+ "type": "string"
+ },
+ "dimensions": {
+ "additionalProperties": true,
+ "description": "This alternative's ratings across the dimensions.",
+ "properties": {
+ "affordability": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "cost_to_value": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "counterparty_safety": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "death_benefit": {
+ "description": "Death-benefit summary.",
+ "type": "string"
+ },
+ "inflation_protection": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "liquidity": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "longevity_protection": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "market_upside": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "portability": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "regulatory_oversight": {
+ "description": "Who regulates it (e.g. SEC vs state insurance).",
+ "type": "string"
+ },
+ "simplicity": {
+ "additionalProperties": true,
+ "properties": {
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+ },
+ "required": [
+ "score",
+ "label",
+ "explanation"
+ ],
+ "type": "object"
+ },
+ "tax_treatment": {
+ "description": "Tax-treatment summary.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "display_name": {
+ "description": "Human-readable product name.",
+ "type": "string"
+ },
+ "product_type": {
+ "description": "Alternative product slug, e.g. 'fixed_annuity'.",
+ "type": "string"
+ }
+}Output schema / properties / comparisons / items / requiredAdded value: +[
+ "product_type"
+]Output schema / properties / comparisons / items / typeAdded value: +"object"Output schema / properties / savvly / properties / affordability / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / affordability / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / affordability / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / affordability / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / affordability / typeAdded value: +"object"Output schema / properties / savvly / properties / cost_to_value / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / cost_to_value / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / cost_to_value / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / cost_to_value / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / cost_to_value / typeAdded value: +"object"Output schema / properties / savvly / properties / counterparty_safety / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / counterparty_safety / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / counterparty_safety / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / counterparty_safety / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / counterparty_safety / typeAdded value: +"object"Output schema / properties / savvly / properties / inflation_protection / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / inflation_protection / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / inflation_protection / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / inflation_protection / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / inflation_protection / typeAdded value: +"object"Output schema / properties / savvly / properties / liquidity / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / liquidity / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / liquidity / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / liquidity / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / liquidity / typeAdded value: +"object"Output schema / properties / savvly / properties / market_upside / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / market_upside / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / market_upside / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / market_upside / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / market_upside / typeAdded value: +"object"Output schema / properties / savvly / properties / portability / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / portability / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / portability / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / portability / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / portability / typeAdded value: +"object"Output schema / properties / savvly / properties / simplicity / $refRemoved value: -"#/properties/savvly/properties/longevity_protection"Output schema / properties / savvly / properties / simplicity / additionalPropertiesAdded value: +trueOutput schema / properties / savvly / properties / simplicity / propertiesAdded value: +{
+ "explanation": {
+ "description": "One-sentence rationale for the rating.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Rating label: None | Very Low | Low | Medium | High | Very High.",
+ "type": "string"
+ },
+ "score": {
+ "description": "Numeric rating; greater = better (e.g. 1–5).",
+ "type": "number"
+ }
+}Output schema / properties / savvly / properties / simplicity / requiredAdded value: +[
+ "score",
+ "label",
+ "explanation"
+]Output schema / properties / savvly / properties / simplicity / typeAdded value: +"object"get_savvly_faq7 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / total / maximumAdded value: +9007199254740991Output schema / properties / total / minimumAdded value: +-9007199254740991get_savvly_product_info5 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}project_retirement_with_savvly12 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / inputs / additionalPropertiesPrevious value: -{}New value: +trueOutput schema / properties / inputs / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / metadata / properties / display_hints / properties / chart / properties / tooltip / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / metadata / properties / field_descriptions / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / result / properties / age_dependent_values / items / properties / age / maximumAdded value: +9007199254740991Output schema / properties / result / properties / age_dependent_values / items / properties / age / minimumAdded value: +-9007199254740991Output schema / properties / visualization / properties / chart / properties / tooltip / propertyNamesAdded value: +{
+ "type": "string"
+}project_savvly_lumpsum21 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / inputs / additionalPropertiesPrevious value: -{}New value: +trueOutput schema / properties / inputs / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / metadata / properties / field_descriptions / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_age / maximumAdded value: +9007199254740991Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_age / minimumAdded value: +-9007199254740991Output schema / properties / summary / properties / early_exit_refund_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / early_exit_refund_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / percentage_gain_upper_percent / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / percentage_gain_upper_percent / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / savvly_above_market_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / savvly_above_market_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / total_market_alone_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / total_market_alone_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / total_savvly_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / total_savvly_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / visualization / properties / chart / properties / tooltip / propertyNamesAdded value: +{
+ "type": "string"
+}project_savvly_monthly21 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / inputs / additionalPropertiesPrevious value: -{}New value: +trueOutput schema / properties / inputs / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / metadata / properties / field_descriptions / propertyNamesAdded value: +{
+ "type": "string"
+}Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_age / maximumAdded value: +9007199254740991Output schema / properties / result / properties / payout_age_dependent_values / items / properties / payout_age / minimumAdded value: +-9007199254740991Output schema / properties / summary / properties / early_exit_refund_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / early_exit_refund_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / percentage_gain_upper_percent / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / percentage_gain_upper_percent / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / savvly_above_market_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / savvly_above_market_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / total_market_alone_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / total_market_alone_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / summary / properties / total_savvly_upper_usd / anyOfAdded value: +[
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / summary / properties / total_savvly_upper_usd / typeRemoved value: -[
- "number",
- "null"
-]Output schema / properties / visualization / properties / chart / properties / tooltip / propertyNamesAdded value: +{
+ "type": "string"
+}search_savvly_content17 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / session_idAdded value: +{
+ "description": "REQUIRED on every call after your first. This MCP server associates all of your tool calls for a given task using session_id; a call that arrives without it cannot be associated with your earlier work and is treated as the start of an unrelated task, disconnected from the original goal. Omit it on your first call only — the server will issue one in the _mcp_instructions field of the result (or a trailing [MCP INSTRUCTIONS] text block) — then echo that exact value on every later call. Never invent a value, and do not issue parallel tool calls until the server has issued your session_id. One session_id covers the whole goal from start to finish: when you spawn subagents you MUST give them this same session_id, or their work is severed from yours. Without session_id, this server does not function as intended.",
+ "type": "string"
+}Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / properties / _mcp_instructionsAdded value: +{
+ "description": "Your handles for this task, confirmed by this MCP server on every response, and the instructions for echoing them on later calls. Read and follow.",
+ "properties": {
+ "instructions": {
+ "type": "string"
+ },
+ "session_id": {
+ "description": "Echo this exact value as the session_id argument on every subsequent tool call.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Output schema / properties / filter_applied / properties / audience / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / filter_applied / properties / audience / typeRemoved value: -[
- "string",
- "null"
-]Output schema / properties / filter_applied / properties / limit / maximumAdded value: +9007199254740991Output schema / properties / filter_applied / properties / limit / minimumAdded value: +-9007199254740991Output schema / properties / filter_applied / properties / query / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / filter_applied / properties / query / typeRemoved value: -[
- "string",
- "null"
-]Output schema / properties / filter_applied / properties / section / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / filter_applied / properties / section / typeRemoved value: -[
- "string",
- "null"
-]Output schema / properties / matched / maximumAdded value: +9007199254740991Output schema / properties / matched / minimumAdded value: +-9007199254740991Output schema / properties / total_in_library / maximumAdded value: +9007199254740991Output schema / properties / total_in_library / minimumAdded value: +-9007199254740991get_savvly_product_info1 field changedOutput schema / properties / illustrative_payoutAdded value: +{
+ "additionalProperties": true,
+ "description": "One worked example of what the schedule pays: the modeled payout RANGE at each milestone age for a single fixed allocation, so the percentages above have dollar figures beside them. Fixed inputs, identical for every caller — hypothetical, not a quote, and not tailored to the user. For the user's own age and amount, call `project_savvly_lumpsum`.",
+ "properties": {
+ "average_return": {
+ "description": "Assumed average annual S&P 500 return, in percent.",
+ "type": "number"
+ },
+ "current_age": {
+ "description": "Age the illustrated allocation is made at.",
+ "type": "number"
+ },
+ "funding_amount": {
+ "description": "USD allocated up front in the illustration.",
+ "type": "number"
+ },
+ "payouts": {
+ "description": "One row per milestone age, low-to-high payout range in USD.",
+ "items": {
+ "additionalProperties": true,
+ "properties": {
+ "age": {
+ "description": "Milestone age (80, 85, 90, or 95).",
+ "type": "number"
+ },
+ "lower_usd": {
+ "description": "USD. Low end of the modeled payout at this age.",
+ "type": "number"
+ },
+ "upper_usd": {
+ "description": "USD. High end of the modeled payout at this age.",
+ "type": "number"
+ }
+ },
+ "required": [
+ "age",
+ "lower_usd",
+ "upper_usd"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "current_age",
+ "funding_amount",
+ "average_return",
+ "payouts"
+ ],
+ "type": "object"
+}get_savvly_faq1 field changedInput schema / properties / section / enumPrevious value: -[
- "all",
- "understanding-savvly",
- "investment-custody",
- "payouts",
- "withdrawals-estate",
- "fees-cost",
- "tax-legacy",
- "employer-portability",
- "safety-regulatory"
-]New value: +[
+ "all",
+ "understanding-savvly",
+ "investment-custody",
+ "payouts",
+ "withdrawals-estate",
+ "expenses-cost",
+ "tax-legacy",
+ "employer-portability",
+ "safety-regulatory"
+]get_savvly_product_info4 fields changedInput schema / properties / section / descriptionPrevious value: -"Which part of the product profile to focus the text on — one of 'all', 'overview', 'regulatory', 'investment', 'fees', 'payouts', 'tax', 'distribution' (default 'all'). The full overview card always renders regardless."New value: +"Which part of the product profile to focus the text on — one of 'all', 'overview', 'regulatory', 'investment', 'expenses', 'payouts', 'tax', 'distribution' (default 'all'). The full overview card always renders regardless."Input schema / properties / section / enumPrevious value: -[
- "all",
- "overview",
- "regulatory",
- "investment",
- "fees",
- "payouts",
- "tax",
- "distribution"
-]New value: +[
+ "all",
+ "overview",
+ "regulatory",
+ "investment",
+ "expenses",
+ "payouts",
+ "tax",
+ "distribution"
+]Output schema / properties / expensesAdded value: +{
+ "additionalProperties": true,
+ "description": "Expense structure in basis points (common vs tracking shares) and the blended range; illustrations are net of expenses.",
+ "properties": {},
+ "type": "object"
+}Output schema / properties / feesRemoved value: -{
- "additionalProperties": true,
- "description": "Fee structure in basis points (common vs tracking shares) and the blended range; illustrations are net of fees.",
- "properties": {},
- "type": "object"
-}check_savvly_eligibility1 field changedInput schema / properties / channel / descriptionPrevious value: -"Distribution channel"New value: +"Distribution channel — one of 'individual', 'employer', 'advisor' (default 'individual')."compare_savvly_vs_alternative2 fields changedInput schema / properties / alternative / descriptionPrevious value: -"The product type to compare against Savvly, or 'all' for the full matrix"New value: +"Which product type to compare Savvly against. Use EXACTLY one of: 'fixed_annuity', 'variable_annuity', 'indexed_annuity', 'target_date_fund', 'managed_payout_fund', or 'all' for the full matrix. Pick a SPECIFIC annuity subtype — there is no generic 'annuity'."Input schema / requiredRemoved value: -[
- "alternative"
-]get_savvly_product_info1 field changedInput schema / properties / section / descriptionPrevious value: -"Which part of the product profile to focus the text on; the full overview card always renders regardless."New value: +"Which part of the product profile to focus the text on — one of 'all', 'overview', 'regulatory', 'investment', 'fees', 'payouts', 'tax', 'distribution' (default 'all'). The full overview card always renders regardless."search_savvly_content1 field changedInput schema / properties / audience / descriptionPrevious value: -"Restrict to one stakeholder audience ('general' is the factual FAQ). Omit to search across all audiences."New value: +"Restrict to one stakeholder audience. Use EXACTLY one of: 'employee', 'advisor', 'broker', 'employer', 'universal', or 'general' ('general' is the factual FAQ). Omit to search across all audiences."Run hypothetical retirement simulations and compare outcomes using your assumptions.
SmartMoney77 MCP v0.6.0 — 14 public tools that turn financial questions into exact numbers and citable links. New: historical_investment_return and compare_investments, which compute "what if I had invested" results from real yearly price data. Also compound interest, FIRE number, credit-card payoff, emergency fund, inflation, latte factor, investment fees, cost of waiting, plus discovery/deep-link/share-pack tools for a catalog of calculators in 6 languages (he/en/ar/es/pt/in). Public, no login. Endpoint: https://smartmoney77.com/mcp
Deterministic US financial planning: retirement Monte Carlo, Roth conversion, RMD, tax, IRMAA, SS
Research US-listed companies and funds with the StockPortfolio.pro MCP server. Tools cover SEC filing-grounded financials, filing timelines, company comparisons, watchlist screens, fund profiles, and cited filing questions. Filed figures include their fiscal period and EDGAR source URL; missing filing data is returned as null. Public tools work without authentication; optional API-key or OAuth access is supported. US-listed, USD-reporting companies only. Keyless access includes 3 free AI questions per rolling 30-day window. To get more now, choose the Dev plan ($19.99/month, 200 credits) at https://www.stockportfolio.pro/register?plan=dev, then follow https://www.stockportfolio.pro/docs/api-mcp to connect with OAuth or an API key. Or wait for the free allowance to renew.
Add one secure layer between your agents and this server.
