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

With no annotations, the description carries the full burden and adds real value: it discloses the plan requirement ('Starter plan and above') and the returned fields (rate used, given amount, converted amount). It does not cover failure behavior (invalid currency code, out-of-range date), which is the remaining gap for a no-annotation tool.

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 short sentences, front-loaded with the action, then the return contract, then the access requirement. Nothing is redundant and no sentence could be dropped without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter tool with no output schema, the description covers the operation, the date variant, the return contents, and plan gating — enough to call it correctly. Only error/edge-case behavior is left unstated.

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 YYYY-MM-DD pattern for 'date' and the exclusiveMinimum on 'amount' — are already documented in the schema. The description's mention of the date conditional restates rather than extends the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('converts an amount from one currency to another') plus the basis for the conversion (latest rate or a past date's rate). It implicitly separates itself from the rate-listing siblings (get_latest_rates, get_historical_rates) by returning a converted amount, but never names or contrasts them 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?

It clearly states the condition that selects the historical behavior: supply 'date' for a past day's rate, omit it for the latest rate. There are no explicit exclusions or named alternative tools for the rate-only lookups, 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 provided, the description carries the burden well: it discloses the returned fields, the sign convention with a worked interpretation (positive = symbol strengthened), and the plan gating. It does not mention rate limits or behavior when dates are invalid/reversed, which keeps it below 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?

The output fields are front-loaded in the first clause, followed by the sign convention and plan note. The sign-convention sentence is long but each part earns its place by preventing a real interpretation error; no 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?

There is no output schema and no annotations, so the description must specify the response shape and safety/permission context — it does both by enumerating return fields and stating the plan requirement. Minor gap: no guidance on default date behavior beyond what the schema provides or on large-symbol responses.

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 base, startDate, endDate, and symbols are already fully documented in the schema, including defaults and the symbols guidance. The description adds no parameter-level meaning beyond the sign convention, so the 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?

States a specific verb and resource ('Returns how currencies moved between two dates') and enumerates the returned metrics (start rate, end rate, absolute change, percent change). It is clearly distinct from a raw rate lookup, though it does not explicitly name the closest siblings (get_time_series, get_historical_rates) that an agent might confuse it with.

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 a clear operational precondition ('Professional plan and above') and implies usage for two-date comparison, but it never says when to prefer this over get_time_series or get_historical_rates. The choice among siblings 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.

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

With no annotations, the description carries the burden and does disclose two meaningful behavioral facts: data-availability boundaries and plan gating (Starter+). It is silent on response shape, payload size (the 1000+ entry default lives only in the schema), and whether requests for pre-coverage dates error or return empty.

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 short sentences, front-loaded with what the tool returns, then coverage limits, then plan requirement. No filler; the parenthetical pointer to list_currencies is actionable rather than decorative.

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, so the description must stand alone — and it covers purpose, data availability, plan requirement, and a currency-lookup escape hatch. The remaining gap is what the response looks like and how out-of-range dates behave, which an agent needs before calling.

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 parameters are already documented, including base-plan gating and the symbols size warning. The description adds the date lower bound (1984-11-28) and per-currency listing dates, which genuinely extend the bare 'YYYY-MM-DD format' schema text, but it adds nothing about base or symbols.

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?

Clear verb+resource+scope: 'Returns exchange rates for a specific past date' precisely separates it from get_latest_rates without naming the sibling. It does not explicitly name alternatives, but the temporal qualifier makes the distinction usable.

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 constraints on when the tool works: historical coverage from 1984-11-28 for major fiat, per-currency listing dates for newer/crypto, and a paid-plan requirement. It never explicitly contrasts with get_latest_rates or get_time_series, leaving the choice of tool to the name rather than stated 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 full burden and does substantial work: it discloses that rates are returned as strings, that refresh frequency varies by plan (daily/hourly/10min/60s), and that the response can balloon to 1000+ entries. It stops short of describing error behavior or the response shape (e.g. a code→rate mapping).

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, front-loaded with purpose and followed by constraints and the key caveat. The plan-tier refresh sentence is dense but earns its place; nothing is redundant enough to cut.

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 two-optional-parameter read tool with no annotations and no output schema, the description covers scope, return type, freshness, and response-size risk. The main gap is the shape of the returned payload, which matters here precisely because no output schema exists.

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 both parameters are already fully documented, including the default base of USD, the comma-separated symbol format, and the advice to prefer passing symbols. The description's 'Omit symbols to get all 1000+ currencies' restates the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (returns latest exchange rates) plus scope (fiat, crypto, metals; against a base currency). The word 'latest' implicitly separates it from get_historical_rates, get_time_series, and get_fluctuation, but no sibling is named, so an agent must infer the boundary rather than read it.

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?

Usage guidance is limited to parameter-level advice ('Omit symbols to get all 1000+ currencies'). There is no statement of when to pick this over convert_currency (single conversion) or get_historical_rates, and no mention of the plan prerequisite for changing base beyond what the schema already says.

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?

No annotations exist, so the description carries the full burden. It does add real context: plan gating and the one-entry-per-day shape of the result. It omits what happens with large ranges, empty intervals, response size/pagination behavior, and error conditions, which matter for a date-range query tool.

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, front-loaded with the capability and followed by the access constraint; no filler. It is arguably under-sized for a tool with zero annotation coverage, but nothing in it is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description should be richer. It covers the plan requirement and output granularity, but leaves the agent without guidance on range limits, large-response behavior, or failure modes for a tool that can return 1000+ entries per day.

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%, and each parameter is already documented with format, defaults, and plan-dependent base behavior. The description adds nothing about parameters beyond restating the two dates and the currency set, 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 (returns daily exchange rates), the scope (one or more currencies, between two dates) and the granularity (one entry per day). It is distinguishable from get_latest_rates and get_historical_rates by the daily-series framing, but it never names them, so differentiation is left to inference.

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 only usage signal is the eligibility constraint (Professional plan and above), which is genuinely useful for deciding whether to call. There is no explicit guidance on when to pick this over get_historical_rates or get_fluctuation, and no exclusions or alternatives are named.

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?

No annotations, so the description carries the full burden. It usefully discloses the plan gating ("Growth plan and above") and that the rate used is the latest, not historical. However, it omits failure behavior for private/ungeolocatable IPs and what happens when no rate exists for the derived currency.

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 short sentences, front-loaded with the core action and ending with the access constraint. No sentence repeats the title or the schema, and the 'to' field note earns its place as return-value 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?

There is no output schema, so the description is the only source of return-value information, and it names just the 'to' field. The converted amount field, the rate used, and error shapes remain undisclosed for a tool whose output the agent will need to interpret.

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 three parameters (ip, from, amount) are already documented including the omit-to-use-caller's-IP behavior and the amount default. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: resolve the local currency from an IP's geolocation and convert an amount into it at the latest rate. This clearly distinguishes it from the generic sibling convert_currency (which takes an explicit target) and from get_latest_rates, since the target currency is derived from an IP.

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?

"Useful for localizing prices for a visitor" implies the use case but never says when to prefer this over convert_currency (target currency already known) or what to do if geolocation is not desired. The agent must infer the alternative from the sibling name alone.

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 burden and does well: it discloses that no API key is needed, that the default response is a compact code → name map, which fields detailed=true adds (country, status AVAILABLE/DEPRECATED, availableFrom/availableUntil), and warns that the full detailed catalogue is very large. Gaps are minor — nothing on rate limits, error behavior, or pagination of the 1000+ item list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what the tool returns, then usage, then auth, then the two parameter behaviors in progression. Four dense sentences with no filler and no repetition of the schema text verbatim.

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 2-parameter, no-annotation, no-output-schema read tool, the description covers the essentials: return shape in both modes, auth requirement, catalogue size caveat, and how the parameters interact. Nothing an agent needs in order to call this 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond it: concrete search examples ('rupee', 'PK', 'bitcoin') and the behavioral distinction that country names are only matched when detailed=true. That extra context lifts it above baseline.

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 ('Returns the currencies supported by CurrencyFreaks') and quantifies the scope: 1000+ fiat currencies, cryptocurrencies, and precious metals with named examples (XAU, XAG, XPT, XPD). It also positions itself against siblings by saying it's used to find a currency code before calling rate or conversion tools, so an agent can distinguish it from get_latest_rates and convert_currency without opening the 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?

Explicitly names the downstream tools (rate or conversion tools) and the condition that selects this one — locating a currency code first. It also gives usage routing between the plain call, 'search', and detailed=true, including the instruction to combine search with detailed because the full catalogue is very large.

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