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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds that cross rates are computed via TRY and that the bulletin for a given date or the latest bulletin is used, which is useful behavioral context beyond the annotations. It does not cover error handling or rate-limit behavior.

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 concise sentences, with the core conversion scope front-loaded and no filler. Every clause adds relevant scope or date behavior.

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 the existing output schema and annotations, the description covers the essential conversion behavior, supported currency relationships, and date default. It omits rate_type selection detail, but that is documented in the schema and not required 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 coverage is 80%, with descriptions for from, to, date, and rate_type, so the baseline is 3. The description clarifies the date fallback and cross-rate mechanism but does not add meaning beyond the schema for amount or rate_type.

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 'Convert an amount between TRY and any TCMB currency, or between two foreign currencies (cross rate via TRY),' a specific verb and resource with unique cross-rate scope. This distinguishes it from the retrieval-oriented siblings get_exchange_rates, list_currencies, and get_rate_history even without naming 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 conversion scenarios and the date fallback ('Uses the bulletin for `date`, or the latest one'), but does not say when to choose this over get_exchange_rates or get_rate_history. Usage is implied rather than explicit, with no exclusions or named alternatives.

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, openWorldHint and idempotentHint, so the safety profile is covered. The description adds real behavioral context beyond the schema: the data is the official TCMB bulletin, and omission of parameters yields the latest bulletin / all ~22 currencies. It stops short of saying what happens for non-publication days (weekends/holidays), which is the one behavior an agent would still want.

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 tight sentences, zero filler, with the resource and unit front-loaded before the default-behavior clause. Every clause earns its place.

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 an output schema present, return values need no explanation, and annotations cover the safety profile, so the description only needs to cover purpose, defaults, and units — which it does. The remaining gap is edge-case behavior for dates with no published bulletin.

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 50% (the `currencies` array itself has no top-level description). The description compensates by defining the return unit (TRY per foreign currency), the default cardinality (~22 currencies), and the meaning of an omitted `date` (latest bulletin) — meaning that the schema does not carry.

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 (TCMB official exchange rates) with the semantic unit defined (TRY per unit of foreign currency) and the temporal scope (for a date). It is clearly distinct from convert_currency and get_rate_history by being a single-date official-bulletin lookup, though it never names those siblings 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?

The description tells the agent how to use the parameters (omit `date` for latest, omit `currencies` for all) but gives no guidance on when to choose this tool over get_rate_history or convert_currency. Usage is implied by the 'for a date' framing rather than stated.

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/openWorld/idempotent, and the description adds genuinely non-obvious behavior: the returned statistics (first/last, min/max with dates, mean, % change) and the hard interval caps (93/731/3660 days) that determine whether a call will succeed. Missing: behavior on weekends/holidays and on dates outside TCMB's published 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 dense sentences: output shape first, then the constraint that governs parameter choice. No filler, nothing duplicated from the schema, and the most decision-relevant information is front-loaded.

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 the description is not obliged to explain returns, yet it does so briefly and usefully. Combined with the range caps and rate-unit convention, an agent has enough to call this correctly; only edge-case behavior (holidays, out-of-range dates, TRY conversions) 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 coverage is 80%, so the baseline is 3, and the description earns an extra point by documenting the per-interval range limits (daily 93, weekly 731, monthly 3660) that constrain the interval parameter but appear nowhere in the schema. It does not touch rate_type or end_date, which the schema already covers 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?

States a specific verb+resource ('Time series of one currency's TCMB rate') and clarifies the unit convention (TRY per 1 unit), which cleanly separates it from convert_currency and get_exchange_rates. It never names a sibling explicitly, but the 'history/time series' framing makes the distinction inferable.

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 implied by 'time series' and by the range limits, which tell the agent when a given interval is viable. There is no explicit statement of when to prefer this over get_exchange_rates or convert_currency, and no mention of prerequisites or error behavior when a range is exceeded.

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, idempotentHint and openWorldHint, so safety and repeatability are covered. The description adds genuinely useful context beyond them — that results come from the 'latest TCMB bulletin' (freshness/source) and that entries carry a 'quoting unit' (interpretation caveat). It says nothing about ordering, caching or coverage of currencies, so it is additive but not rich.

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 clause with no filler, and the most decision-relevant qualifier ('latest TCMB bulletin') is placed first. Nothing could be removed without losing meaning.

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 parameters, an output schema covering return values, and annotations covering safety, the remaining burden on the description is small. It supplies the two things the structured fields do not: the source/freshness of the data and the quoting-unit caveat. A note on ordering or currency coverage would complete it.

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 there is nothing for the description to disambiguate; the baseline for a 0-param schema is 4. The mention of quoting unit is a data-shape note rather than parameter guidance.

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 names a specific resource (currencies) scoped to a specific source and freshness ('latest TCMB bulletin'), plus a data-shape detail ('their quoting unit'). This separates it from get_exchange_rates and get_rate_history, though the retrieval verb is only implied by the tool name rather than stated.

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 description is a pure noun phrase with no when-to-use, when-not-to-use, or alternative-routing guidance. An agent must infer from the name and sibling set that this is the discovery step before convert_currency; nothing in the text says so.

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