Frankfurter

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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds substantial behavior: the rounded {amount, currency} return shape, rounding to the target's minor units, upstream per-direction rounding, and that a date inside a weekly/monthly/quarterly provider period returns the rate in force. It does not cover failure behavior for unknown codes or future dates, so it falls short of 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?

Four tight sentences, front-loaded with the core action and return shape, then the precision caveat, then provider usage. No filler or redundant restatement of the name.

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, so the description carries the return shape, which it does ('Returns {amount, currency} rounded to the target's minor units'). Combined with full parameter coverage and the precision caveat, an agent has everything needed to invoke 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 baseline is 3. The description reinforces provider semantics ('one institution's published rate, e.g. UST') beyond what the schema contains; this is useful but does not extend beyond the schema's own provider documentation.

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: 'Convert an amount from one currency to another'. It distinguishes itself from the sibling get_rates by noting that get_rates is the tool for rates and the flip path, so an agent can select 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?

Gives two concrete conditions: use get_rates with a flipped direction for low-value sources for more precision, and pass provider when you need one institution's published rate. It lacks an explicit statement of when conversion is inappropriate (e.g., cross-asset conversions or exact rate retrieval), but the context is clear.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: provider mode serves published rates instead of the blend, digits are as published on the provider's own base, and a date inside a provider's period returns the rate in force.

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 core purpose and the sibling relationship, with no redundant restatement of the name or schema.

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 5-parameter read-only tool with no output schema, the description covers the non-obvious provider semantics well; the remaining parameters (base, date, quotes) are fully documented in the schema, so nothing critical is missing, though return shape is left implicit.

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 the schema does not: it clarifies the provider parameter's effect (published rates vs blend, effective-date semantics) and the base-relative digit behavior, which helps an agent interpret results.

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 ('Latest or a single day's exchange rates') and explicitly positions itself as the 'raw-rate companion to `convert`', so an agent can distinguish it from the conversion sibling without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'raw-rate companion to `convert`' framing implies when to prefer this tool (retrieving rates rather than converting), and the provider clause explains the alternative mode. It stops short of an explicit 'use this instead of convert when...' statement or exclusions, so it is clear context but not 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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuine context beyond that: it discloses the scope of assets covered (fiat, precious metals, crypto) and the shape of the response as a code-to-name mapping, which is not in any structured field.

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 single front-loaded sentence with the scope stated first and a compact example that removes ambiguity about the return value. 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?

For a trivial zero-argument discovery tool with no output schema, the description plus inline example is sufficient to call it and interpret results. Only a note on whether the list is static or account-dependent would add value.

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 tool takes zero parameters, so the baseline is 4 and no parameter explanation is needed. The description correctly spends its words on output scope instead.

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 (supported currency, precious metal and crypto asset codes) with an inline example of the returned mapping. It is naturally distinguishable from convert and get_rates, though it never explicitly contrasts itself with list_providers.

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 is only implied: an agent can infer this is the lookup used to discover valid asset codes before calling convert. There is no explicit when-to-use or when-not-to-use statement, and no mention of the sibling tools.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context: the output is a catalog of institutions with frequency categories (daily, weekly, monthly, quarterly) and coverage date ranges, and that omitting a provider yields a blend. No mention of ordering or whether results are cached.

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, no filler. The catalog contents come first and the cross-tool usage note follows, which is the right order for an agent scanning for relevance.

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 input parameters and no output schema, the description carries the return-value burden and largely discharges it by naming the fields returned. A little more on the response shape (e.g. a flat array vs. object) would make it fully self-sufficient.

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 tool takes no parameters, so the baseline applies and the description correctly spends no space on argument docs. It instead explains the semantic meaning of the returned `key` field as an input to sibling tools, which is the relevant 'parameter' knowledge here.

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 ('List the institutions whose rates Frankfurter relays') and enumerates what each entry carries: key, rate type, frequency, coverage dates. This clearly distinguishes it from list_currencies and from the rate-fetching siblings convert/get_rates.

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 says to take a returned key and pass it as `provider` to `convert` or `get_rates` for single-institution rates instead of the default blend. That is strong routing guidance, though it explains downstream use rather than stating when this tool itself should be chosen over an alternative.

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