Türkiye Central Bank (TCMB) Exchange Rates

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

Goes well beyond the readOnly/idempotent annotations: publication schedule (business days ~15:30 UTC+3), the indicative-not-official caveat, 6-decimal results, string decimals, TRY-per-unit quoting with JPY per 100, and the presence of source_url/bulletin_date/disclaimer in every response. This is exactly the context an agent needs to trust and interpret output.

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 the purpose, then rules, then output shape and source/schedule. Every sentence carries useful information, though the return-value sentence and the later 'Every result includes source_url...' sentence partially overlap and could be merged.

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 conversion tool with an output schema and strong annotations, nothing material is missing: quoting conventions, date defaulting, cross-conversion behavior, precision, and data provenance are all covered.

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: the cross-conversion convention that rate_type applies to both legs, the TRY-on-either-side rule, and the omission of date meaning 'latest bulletin'. It does not elaborate the enum semantics of rate_type (that lives in the schema), so it is not a full 5.

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 (converts an amount between two currencies) with the authoritative source qualifier (TCMB rates). It is clearly distinguishable from the sibling rate-listing tools because it performs a conversion and returns a computed result plus breakdown rather than a rate table.

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 concrete operational guidance: TRY may be on either side, omit date for the latest bulletin, and cross conversions route through TRY using the same rate_type on both legs. It does not explicitly say when to prefer a sibling (e.g. get_latest_rates for raw rates), so it stops short of full alternative routing.

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 cover read-only/idempotent/closed-world, and the description adds real context beyond them: publication schedule (business days ~15:30 UTC+3), the TRY-per-unit convention with the JPY-per-100 exception, string-formatted decimals, mandatory source_url/bulletin_date/disclaimer fields, and an explicit 'indicative, not for official use' caveat.

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 tight paragraph that front-loads the purpose, then layers source, timing, units, and caveats in descending order of importance. Every clause carries information an agent needs to interpret the response correctly.

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 (0 required params, 1 optional, output schema present) and the description covers source, timing, units, formatting, and disclaimers. Nothing an agent needs in order to call it or interpret the result 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 currencies array, its ISO 4217 pattern, the maxItems cap, and the omit-for-all default are already documented. The description adds unit-interpretation guidance for the returned rates but nothing new about the parameter itself, so the baseline of 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 the most recent TCMB exchange-rate bulletin) plus the exact semantics (TRY per unit of foreign currency). The word 'most recent' implicitly separates it from get_rates_on_date, 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?

Usage is only implied: 'most recent' suggests calling this when current rates are needed rather than a historical date. There is no explicit when-to-use/when-not guidance and no reference to convert_currency, get_rates_on_date, or list_currencies.

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 only cover the read-only/idempotent profile, and the description adds substantial behavior beyond them: the weekend/holiday/today-before-15:30 fallback with a fallback_reason, the pre-2005 TRL denomination change, quote conventions (TRY per unit, JPY per 100), string-typed decimals, and the mandatory source_url/disclaimer fields. These are exactly the traps that would cause a misread result if undisclosed.

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 sentences, all carrying operational information, with the core purpose front-loaded. Slightly dense — the trailing disclaimer sentence is the weakest, though it explains fields the caller will see in the response.

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?

An output schema exists, so return values need not be enumerated; the description instead covers the edge cases an agent must anticipate — fallback, denomination change, quote unit, string decimals — which is what's actually missing from structured fields.

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; the description goes beyond it by explaining that the date is the bulletin date (not a request timestamp) and that omitting currencies yields all ~20. It also adds quote-interpretation semantics (per unit, JPY per 100, TRL history) that the schema cannot express.

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 TCMB daily bulletin published on a given date — with a clear scope (history back to 1996). That framing separates it from get_latest_rates (always the newest) and convert_currency (cross-rate computation) without needing to name them.

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?

Describes the operative scenario well: supply a date, and if no bulletin exists that day, a fallback to the prior bulletin is returned with is_fallback=true. It does not explicitly say when to prefer get_latest_rates or convert_currency instead, nor does it warn against using this for live intraday rates beyond the ~15:30 TRT note.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond that by disclosing the scope constraint 'latest TCMB bulletin' — only currencies present in the newest bulletin are listed — plus the shape of each entry; it does not add pagination or error 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?

Two sentences: the first defines the resource and its contents, the second routes the agent to the follow-up action. Nothing is wasted and the essential scoping info comes first.

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-argument, read-only list tool with full annotation coverage and a declared output schema, nothing material is missing — scope, entry contents and intended use are all stated.

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 and the schema is empty at 100% coverage, so there is no parameter semantics to explain. Baseline 4 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 ('Lists currencies in the latest TCMB bulletin') and enumerates the per-entry content: English/Turkish names, quoting unit, and published rate types. This is clearly distinguishable from get_latest_rates, get_rates_on_date and convert_currency, which return values rather than a currency inventory.

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?

'Use it to check codes before calling the other tools' explicitly positions it as a prerequisite/discovery step relative to its siblings. It stops short of naming exclusions or prerequisites (e.g. whether the latest bulletin is always populated), so it is not a full 5.

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