US bill serial numbers: star note print runs and fancy serial patterns with exact odds.
Scored across 4 tools
Each tool has a clearly distinct purpose: check_serial evaluates a single note, find_star_runs lists top runs, get_coverage reports data coverage, and list_serial_patterns enumerates patterns. There is no overlap in functionality.
All tool names are lowercase with underscores and use a verb_noun pattern, though 'get_coverage' uses 'get' while others use domain-specific verbs. This is a minor deviation but still consistent enough.
With 4 tools, the server is well-scoped for a niche domain of US paper money serial number analysis. Each tool serves a distinct and necessary purpose without redundancy.
The tool set covers checking a serial, finding star runs, getting coverage, and listing patterns, which appears complete for the stated purpose. A potential gap is the lack of a tool to directly search for notes matching certain patterns, but this is a minor omission.
Whether one US paper money note is worth keeping, from its serial number: the Federal Reserve Bank, the series (worked out from the serial when it is not given), every collector pattern in the eight digits with its exact odds, and for a star (replacement) note the print run it came from with the number of notes printed and its rarity band. Covers Federal Reserve Notes from Series 1963 on. Gives no price and no authenticity judgement.
| Name | Required | Description | Default |
|---|---|---|---|
| serial | Yes | The serial as printed, spaces optional, e.g. "MB 123 45678 C", "B12345678C", or "A 000 00047 *" with * or ★ for the star. | |
| series | No | The series printed on the note, only if known, as printed beside the portrait, e.g. "2017A", "2021", "1995". | |
| denomination | No | Face value in dollars: 1, 2, 5, 10, 20, 50 or 100. Needed for the star note print run. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive, non-open-world behavior, so the bar is lower; the description still adds substantive context by disclosing that the series is derived from the serial when omitted and by bounding coverage to Series 1963+ Federal Reserve Notes. It also proactively rules out price and authenticity output, which prevents misuse.
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 output inventory are front-loaded, and the two trailing sentences carry the scope and exclusion limits with no filler. The opening sentence is a long, heavily comma-listed run-on, which slows parsing slightly but every clause adds information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description correctly takes on the job of describing return content (patterns with exact odds, print-run counts, rarity band) and coverage limits, which is what an agent needs to call it. It stops short of describing the response shape or behavior on an invalid/unsupported serial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it clarifies that series is optional because it can be worked out from the serial, and it flags that denomination is required specifically for the star-note print run. That inference behavior is not stated in the schema itself.
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?
Specific verb+resource ('check a US bill's serial number') with a precise inventory of what comes back: FRB, series, every collector pattern with odds, and star-note print run details. It does not explicitly contrast itself with siblings like find_star_runs or list_serial_patterns, which overlap on the pattern/run territory, so an agent must infer the per-serial scope.
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 real scope limits for routing: 'Covers Federal Reserve Notes from Series 1963 on' and explicit exclusions ('no price and no authenticity judgement'), which tell the agent when this tool is the wrong choice. It never names an alternative sibling, so it falls short of full when/when-not/alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The smallest US star note print runs on record, smallest first (top 10), optionally for one denomination, series or Federal Reserve Bank: the notes printed, the rarity band and the serial range to watch for. Runs printed only for uncut collector sheets, which never circulate, are left out unless include_sheet_runs is true.
| Name | Required | Description | Default |
|---|---|---|---|
| series | No | Only this series, as printed beside the portrait, e.g. "2017A", "2021", "1995". | |
| district | No | Federal Reserve Bank letter: A Boston, B New York, C Philadelphia, D Cleveland, E Richmond, F Atlanta, G Chicago, H St. Louis, I Minneapolis, J Kansas City, K Dallas, L San Francisco. | |
| denomination | No | Face value in dollars: 1, 2, 5, 10, 20, 50 or 100. | |
| include_sheet_runs | No | Also list runs printed only for uncut sheets (default false). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a safe, read-only, idempotent, closed-world lookup, so the bar is lower. The description goes beyond them usefully: it discloses the top-10 cap, ascending sort, default exclusion of uncut-sheet runs, and the returned fields (notes printed, rarity band, serial range).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler; the scope, ordering and output fields come first and the conditional exclusion is stated only once where it matters.
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?
No output schema exists, yet the description names what a run entry contains and how many are returned, and annotations supply the safety profile. Nothing needed 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% with enums fully documented, so the schema carries parameter meaning. The description only restates the three optional filters and confirms the include_sheet_runs default, adding little beyond structured data.
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 resource (US star note print runs) with scope and ordering (smallest first, top 10) and names the optional filter dimensions. An agent can distinguish it from check_serial, get_coverage and list_serial_patterns without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context that filters are optional and that results are the top 10 smallest runs, plus an explicit rule for sheet-only runs ('left out unless include_sheet_runs is true'). It does not explicitly say when to prefer this over the sibling tools, so it stops short of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Which denominations and series the star note print run figures cover, with the Federal Reserve districts and number of star runs on record for each, the sources, the date of the last update and any known gap.
| Name | Required | Description | Default |
|---|---|---|---|
| denomination | No | Face value in dollars: 1, 2, 5, 10, 20, 50 or 100. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful context about the scope of coverage data (sources, last update, known gaps), but does not disclose behavioral traits beyond what annotations provide, such as default behavior when denomination is omitted.
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 a single dense sentence that efficiently lists the returned coverage fields without redundancy. It is appropriately sized, though the lack of a leading action verb makes the structure slightly less front-loaded than ideal.
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 one optional parameter and no output schema, the description adequately explains what the tool returns, including coverage scope, districts, run counts, sources, update date, and gaps. It omits any usage context or default-filter behavior, which is a minor gap for an informational read-only tool.
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 single optional denomination parameter is fully documented in the schema with an enum and description. The tool description mentions denominations but adds no syntax, default, or filtering semantics beyond what the schema already provides, so the 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 identifies the resource (star note print run figures coverage) and enumerates the specific information it returns, which is clear enough to distinguish it from operational siblings like find_star_runs. It lacks a direct action verb and does not explicitly differentiate itself from check_serial or list_serial_patterns, but the resource focus is unambiguous.
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?
There is no guidance on when to use this tool versus alternatives such as find_star_runs or list_serial_patterns. The description only states what information is returned, leaving the agent to infer the appropriate context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The 17 fancy serial number patterns collectors look for on US bills (ladder, solid, radar, repeater, binary, birthday, low serial and the rest): a strict definition, an example, how many of the 100,000,000 possible eight-digit serials match, and the odds.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so safety profile is covered. The description adds that it returns 17 patterns with definitions, examples, match counts, and odds, providing output-shape transparency despite no output schema. However, no mention of whether this is a static reference or computed data.
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?
Efficient single sentence that front-loads the count and list of patterns, followed by the data fields provided per pattern. No wasted words, though the parenthetical list is long.
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 zero-parameter read-only list tool, the description tells the agent what the tool returns (17 patterns, definitions, examples, match counts, odds) and its domain (US bills). With annotations and full schema coverage, this is nearly complete; minor gap is no explicit output schema but description compensates.
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?
Zero parameters, so baseline is 4. Schema coverage is 100% but no parameters exist; description appropriately doesn't discuss parameter semantics.
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 (list) and resource (fancy serial number patterns) with enumeration of what the resource contains. Clearly distinguished from sibling check_serial (checks a single serial) and find_star_runs.
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?
No guidance on when to use this versus check_serial or find_star_runs. The description is purely a content summary with no routing context or usage conditions.
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.
check_serialfind_star_runsget_coveragelist_serial_patternsLoan-cost math: payments, payoff time, offers with fees, payday loans, Rule of 78s, Fed rates.
Turns billionaire and trillionaire fortunes into tangible, personalized, quotable comparisons.
90+ pure finance calculators: loans, investing, bonds, options, tax. Stateless, stores nothing.
Cited, receipt-backed US home-buying data & calculators — education-only, every number sourced.
Add one secure layer between your agents and this server.
