NBP MCP

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

With no annotations provided, the description carries the full burden and does so well: it discloses table A/table B lookup order, automatic consultation of table B for exotic currencies, response fields showing rate, table, and effectiveDate, and non-business-day fallback behavior. These are exactly the operational traits an agent needs to invoke and interpret the tool 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 front-loaded with the core conversion purpose and then layers on only relevant details about table selection, response fields, and publication fallback. Every sentence contributes useful operational context without repetition or 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?

Given there is no output schema, the description sufficiently explains the relevant response structure by noting that each side of the response shows the rate, table, and effectiveDate used. Combined with its explanation of date handling and fallback behavior, an agent has enough information to call and interpret the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema by explaining that date selects historical rates and that weekends/holidays resolve to the most recent preceding publication. It does not mention no_cache, but the schema already documents that parameter adequately.

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 and resource: convert an amount between two currencies using official NBP mid rates, cross-rated through PLN. This clearly separates it from the sibling rate-retrieval tools such as nbp_exchange_rate and nbp_rate_series without requiring the agent to compare schemas.

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: latest rates by default, historical rates when date is provided, and automatic fallback to the most recent preceding publication on weekends/holidays. It does not explicitly name the sibling tools as alternatives or state when not to use this conversion tool, so it stops short of full routing guidance.

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

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

With no annotations, the description carries the burden and does it well: it discloses the weekend/holiday fallback to the last preceding publication, that effectiveDate in the response shows the date actually used, and that table 'c' returns bid/ask rather than a mid rate. It does not discuss caching behavior beyond what the schema's no_cache field implies, but the key gotcha for an agent (silent date fallback) is surfaced.

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?

Four compact sentences, front-loaded with the core action and default, then table semantics, then the fallback caveat, then the alternative tool. No filler and nothing buried.

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 a return field (effectiveDate) and its meaning, which is exactly the gap that would otherwise hurt. The only shortfall is the lack of differentiation from the other rate-related siblings (nbp_convert, nbp_exchange_rates).

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 baseline is 3, but the description adds behavior the schema does not: that 'date' is the rate 'in force on' that day rather than a strict publication date, and the mid-vs-bid/ask consequence of the table choice. That is meaningful semantics beyond the enum and pattern already documented.

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 ('Get the official NBP rate for one currency against PLN') and immediately scopes the two modes: latest by default or a historical date. It also names the sibling it is not (nbp_rate_series) for multi-day history, so an agent can route without opening schemas.

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 routes multi-day history to nbp_rate_series and explains the latest-vs-historical selection via the date parameter. It does not distinguish itself from nbp_convert or nbp_exchange_rates (plural), which remain plausible alternatives for a converting or bulk-rates use case.

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

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the Polish business-day publishing calendar, the weekend/holiday fallback to the most recent preceding publication, the presence of effectiveDate to reveal the date actually used, and the 2002-01-02 data start. These are exactly the non-obvious traits that would otherwise cause wrong assumptions about dates.

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?

A front-loaded single paragraph with no filler — purpose first, then the calendar/fallback caveat, then the data-range bound. It is dense enough that splitting into purpose-and-behavior sentences would scan faster, but every clause carries 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?

All three optional parameters are covered and the return payload is partially characterized via effectiveDate, which matters because there is no output schema. It stops short of describing the shape of the rate list itself (currency code plus mid/bid/ask fields), which is the only remaining gap for a caller.

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 date, table, and no_cache, making 3 the baseline. The description earns above baseline by adding real semantics for `date`: the business-day fallback rule and the historical lower bound (2002-01-02) are not derivable from the schema's 'Optional historical date (YYYY-MM-DD)'.

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 gives a specific verb and resource ('Get a full NBP ... exchange-rate table against PLN'), and 'full ... table' implicitly separates it from the singular nbp_exchange_rate. Siblings are never named, so differentiation relies on the agent inferring singular-vs-table from the tool name.

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 clearly explains the two operating modes (latest by default, or a historical date), which is useful internal guidance. But it never states when to prefer this over nbp_exchange_rate, nbp_rate_series, or nbp_convert, so sibling selection is left to inference from the names.

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

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

With no annotations, the description carries the full load and does so well: it discloses non-obvious behavior — weekend/holiday requests fall back to the most recent prior publication, and effectiveDate reports the date actually used. The historical boundary (data starts 2013-01-02) is another useful disclosure. It is silent on caching behavior and error/empty-result handling, which keeps it off a 5.

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?

Dense and front-loaded — scope and unit come first, modes second, edge behavior third. Minor redundancy between 'Published every business day' and 'NBP publishes only on Polish business days', which say nearly the same thing twice.

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 and no annotations, and the description does name at least one response field (effectiveDate) plus the date floor, which covers the main ambiguity. It stops short of indicating the return shape for the single-value versus list modes, leaving some guesswork about whether last_n/range return an array.

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 genuinely schema-adjacent meaning: no parameters yields the latest price by default, and the modes are mutually exclusive alternatives rather than combinable filters. The remaining limits (255, 93 days) merely restate schema text.

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?

Names a specific resource and unit (official NBP gold price, PLN per 1 gram of 1000-fineness gold), which immediately distinguishes it from the currency-focused siblings (nbp_convert, nbp_exchange_rate, nbp_rate_series). The four supported query modes are stated in the same breath as the purpose.

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?

Enumerates the four calling modes (default latest, single date, last_n, start/end range) with their caps (255 quotes, 93-day span), so mode selection is clear. It does not explicitly say when to prefer a sibling such as nbp_rate_series, though the gold-only scope makes that largely self-evident.

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

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

With no annotations, the description carries the behavioral burden and discloses key constraints: maximum 93-day windows, chaining for longer spans, publication-day availability for tables 'a'/'c' versus Wednesdays for 'b', and data starting 2002-01-02. It does not mention auth, rate limits, caching, or return shape, but it adds substantial behavioral context beyond the schema.

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 compact and front-loaded: it opens with the core purpose, then presents the two query modes and key constraints. Every sentence contributes useful information without repetition or 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?

For a six-parameter historical-series tool with a fully described schema but no annotations or output schema, the description covers purpose, mode selection, NBP's hard limit, publication calendars, and data start. It could say more about return format or caching, but it is complete enough for correct invocation.

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 schema already documents code, table, last_n, start_date, end_date, and no_cache in detail. The description reinforces the two query modes and adds the useful chaining note for spans over 93 days, but most parameter meaning is already present in the schema.

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 and resource: retrieving a historical time series of NBP rates for one currency against PLN. It clearly separates this from a current-rate or conversion tool through the phrase "historical time series," though it does not explicitly name sibling alternatives.

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 modes: either last_n quotes or an explicit start_date/end_date window, and notes that longer spans require chained calls due to NBP's 93-day limit. It does not explicitly compare this tool with siblings like nbp_exchange_rate or nbp_convert, but the operational context is clear.

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