Server Quality Checklist

Tool Scores

• list_ordersA
  4.3/5.0
  Behavior4/5

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

  Adds valuable behavioral context beyond annotations: open by default, possible inclusion of recently completed orders per Luno API behavior, and requirement for API credentials. Annotations already mark read-only, so no contradiction.

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

  Conciseness5/5

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

  Two sentences, front-loaded with the core action. Every sentence adds value without redundancy.

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

  Completeness5/5

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

  Given the presence of an output schema (not shown), the description adequately covers purpose, usage, behavior, and auth. No gaps for a listing tool.

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

  Parameters3/5

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

  Schema coverage is 100% with descriptions for both parameters. The description merely echoes the pair filter option without adding new meaning, meeting the baseline for high coverage.

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

  Purpose5/5

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

  The description states 'List orders on the authenticated profile' with optional pair filtering, clearly identifying the action and resource. It distinguishes from sibling tools like cancel_order or create_order by focusing on listing.

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

  Usage Guidelines4/5

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

  Explicitly states when to use: 'inspect or audit working orders before cancelling them or placing new ones.' Does not provide when-not-to-use or alternatives, but context is clear.

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

• list_tradesA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true. Description adds 'Public endpoint, no auth required' which is useful behavioral context beyond annotations. No contradictions.

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

  Conciseness5/5

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

  Three concise sentences: purpose and data, public nature, and usage guidance. No wasted words, front-loaded with key info.

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

  Completeness4/5

  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 are covered. Description covers purpose, usage, and data fields. Could mention ordering or limits, but sufficient for a simple list endpoint.

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

  Parameters3/5

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

  Schema coverage is 100% and both parameters are well-documented in the schema. The description adds no additional parameter guidance, so baseline 3 is appropriate.

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

  Purpose5/5

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

  Clearly states verb 'List', resource 'recent public trades', and specifies returned fields (price, volume, side, timestamp). Distinguishes from siblings by noting it's public and not for own trade history.

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

  Usage Guidelines5/5

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

  Explicitly tells when to use: 'for recent execution flow or tape analysis' and importantly what not to use it for: 'not for your own trade history'. Provides clear context and exclusion.

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

• get_order_bookA
  4.5/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds that it is a 'public endpoint, no auth required,' which is additional behavioral context beyond annotations.

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

  Conciseness5/5

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

  Two sentences front-load the core action and immediately provide usage guidance. No unnecessary words.

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

  Completeness5/5

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

  Given the output schema exists (not shown but noted), the description does not need to detail return values. It covers purpose, usage context, and authentication needs adequately.

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

  Parameters3/5

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

  Schema coverage is 100% and the schema already includes a detailed description of the 'pair' parameter, including symbol convention and BTC rewrite. The tool description adds no additional parameter information, so baseline of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states it returns the top 100 bids and asks for a trading pair, aggregated by price level. It uses a specific verb ('Return') and resource ('bids and asks for a trading pair'), distinguishing from siblings like get_ticker and list_trades.

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

  Usage Guidelines5/5

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

  Explicitly says 'Use this to assess available liquidity and likely slippage before sizing an order; use get_ticker for a simple price quote or list_trades for recent execution flow.' This provides clear when-to-use and alternatives.

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

• get_tickerA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds that it is a public endpoint with no auth required and lists the returned fields (price, bid, ask, volume). This provides useful context beyond annotations, warranting a 4.

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

  Conciseness5/5

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

  The description consists of two concise sentences. The first sentence defines the tool, and the second provides usage guidance. No extraneous words, and the most important information is front-loaded.

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

  Completeness5/5

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

  Given the tool's simplicity (one required parameter, no nested objects, with output schema), the description covers the purpose, when to use, what it returns, and authentication status. Combined with annotations, it is fully complete for an agent to use correctly.

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

  Parameters3/5

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

  Schema coverage is 100%, and the schema already describes the parameter thoroughly (e.g., 'Trading pair using Luno's symbol convention... BTC is automatically rewritten to XBT'). The description does not add further parameter semantics, so baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool gets the latest ticker (last trade price, best bid, best ask, 24h rolling volume) for a single Luno trading pair. It uses specific verbs ('Get the latest ticker') and resource ('Luno trading pair'), and differentiates from siblings like get_tickers and get_order_book.

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

  Usage Guidelines5/5

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

  The description explicitly says when to use this tool ('quick price snapshot of one market') and when to use alternatives ('use get_tickers for multiple markets at once, or get_order_book for depth-of-book'). This provides clear recommendations and exclusions.

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

• cancel_orderA
  4.7/5.0
  Behavior5/5

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

  Adds context beyond annotations: idempotency detail and flag requirement. No contradictions with annotations.

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

  Conciseness5/5

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

  Three concise, front-loaded sentences with no redundant information. Every sentence earns its place.

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

  Completeness5/5

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

  Given the tool's simplicity (one parameter, annotations present, output schema exists), the description covers all necessary behavioral and usage context completely.

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

  Parameters3/5

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

  With 100% schema coverage, the description adds minimal value (only reinforces usage context). Schema already explains parameter meaning.

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

  Purpose5/5

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

  The description clearly states the tool's action ('Cancel a working order by ID'), uses a specific verb+resource pair, and distinguishes itself from siblings by referencing list_orders.

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

  Usage Guidelines5/5

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

  Explicitly explains idempotent behavior, when to use (after list_orders), and the required write-operation flag, providing comprehensive usage guidance.

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

• convertA
  4.7/5.0
  Behavior5/5

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

  Annotations indicate destructiveHint=true and idempotentHint=false. The description reinforces this by stating the conversion is final, warns about double-conversion, and clarifies the broker quote at execution time. No contradiction.

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

  Conciseness5/5

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

  The description is two sentences plus a note about the write flag. It is front-loaded with the core purpose and uses minimal but essential words. Every sentence adds value.

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

  Completeness4/5

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

  Given the tool is a destructive write with an output schema (not shown), the description covers key operational aspects: finality, quote timing, idempotency, and auth requirements. It does not detail failure modes or return values, but those are likely in the output schema.

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

  Parameters5/5

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

  Schema description coverage is 100%, and the description adds critical context: idempotency_key behavior (auto-generated UUID vs. user-supplied), amount must be positive decimal string, and account IDs come from get_balances. This significantly aids parameter understanding.

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

  Purpose5/5

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

  The description clearly states the action ('convert funds between two currency accounts'), specifies the broker (Luno), and provides an example ('ZAR to ZARU'). This matches the sibling context: no other tool performs conversions, so it is well-differentiated.

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

  Usage Guidelines4/5

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

  The description explains when to use the tool (e.g., for instant conversions), the importance of idempotency_key for retry safety, and the required write flag. It does not explicitly mention alternatives but covers key usage guidance.

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

• get_balancesA
  4.7/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, destructiveHint, idempotentHint, openWorldHint. The description adds value by specifying authentication requirement (API credentials) and details about balance types (available, reserved, unconfirmed), which are beyond annotation scope.

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

  Conciseness5/5

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

  Two sentences, no unnecessary words. The first sentence describes the action and result; the second gives usage guidance. Highly efficient.

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

  Completeness5/5

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

  Given no parameters and presence of output schema, the description fully covers purpose, usage, authentication requirements, and distinguishes from sibling tools. Nothing essential is missing.

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

  Parameters4/5

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

  No parameters defined; schema coverage is 100% (no params). The description does not need to add parameter info beyond the schema. Baseline for 0 params is 4.

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

  Purpose5/5

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

  The description clearly states the tool returns balances for every account on the authenticated Luno profile, including specific amounts (available, reserved, unconfirmed). It distinguishes from siblings by explicitly contrasting with get_ticker/get_tickers for public market data.

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

  Usage Guidelines5/5

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

  Explicitly states when to use ('check holdings before placing orders, conversions, or transfers') and when not to ('not for public market data'), with alternative tool names (get_ticker, get_tickers).

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

• get_candlesA
  4.7/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds 'Public endpoint, no auth required' and mentions base-currency volume, providing safety info beyond annotations.

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

  Conciseness5/5

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

  Three sentences, front-loaded with purpose, no redundant information. Every sentence is informative.

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

  Completeness5/5

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

  Given the presence of output schema and rich annotations, the description fully covers purpose, usage, parameters, and behavior. No gaps.

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

  Parameters4/5

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

  Schema coverage is 100%, but description adds context on common duration values and that Luno accepts a fixed set, plus automatic BTC rewrite. This adds meaning beyond the schema.

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

  Purpose5/5

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

  Description clearly states it returns OHLCV candlestick data for a trading pair, specifies candle fields, and distinguishes from siblings get_order_book and list_trades.

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

  Usage Guidelines5/5

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

  Explicit when to use (for charts, indicators, backtesting) and when not to (live order-book state or trade-by-trade flow), including specific alternative tool names.

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

• list_transactionsA
  4.7/5.0
  Behavior5/5

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

  The description adds significant behavioral details beyond annotations: pagination by row ID with inclusive/exclusive bounds, API cap of 1000 rows per window, and credential requirements. There is no contradiction with the readOnlyHint and other annotations.

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

  Conciseness5/5

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

  The description is a single paragraph with three sentences, each serving a purpose: stating the main function, explaining pagination mechanics, and suggesting usage. No redundant information.

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

  Completeness5/5

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

  The description covers the core behavior, pagination constraints, and use cases. With an output schema assumed to exist, the description sufficiently prepares an agent for correct invocation without needing further external knowledge.

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

  Parameters4/5

  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 adds value by explaining inclusivity/exclusivity of rows, the API cap, and default values. It also clarifies account_id as a numeric string from get_balances.

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

  Purpose5/5

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

  The description clearly states it lists ledger entries for a single account on the authenticated profile, paginated by row ID. This distinguishes it from siblings like list_orders or list_trades which target different resources.

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

  Usage Guidelines4/5

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

  The description provides explicit use cases: reconciliation, exports, or audit trails. It also explains the pagination iteration pattern. However, it does not explicitly state when not to use it or list alternatives.

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

• get_transactionA
  4.8/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds valuable context: the row limit of 1000 and credential requirement. No contradictions.

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

  Conciseness5/5

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

  Two sentences, no filler. First sentence states purpose and return fields; second provides constraint and prerequisite. Front-loaded and efficient.

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

  Completeness5/5

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

  Given the simple lookup nature, full schema coverage, annotations, and presence of output schema, the description covers all needed context: return fields, limitations, prerequisites, and credentials.

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

  Parameters5/5

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

  Schema coverage is 100% with basic descriptions. The description adds context on how to obtain the IDs: account_id from get_balances, transaction_id from list_transactions (row_index field). This enriches the schema.

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

  Purpose5/5

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

  The description clearly states it returns the full ledger entry for one transaction on the authenticated profile, listing specific fields (amount, running balance, description, timestamp). It distinguishes from sibling tools like list_transactions (which lists) and get_balances (which returns balances).

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

  Usage Guidelines5/5

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

  Explicitly says when to use ('return the full ledger entry for one transaction'), provides a constraint ('only finds transactions within the most recent 1000 rows'), and directs to use list_transactions first for older entries. Also notes requirement for API credentials.

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

• create_orderA
  4.9/5.0
  Behavior5/5

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

  The description adds significant behavioral context beyond annotations: non-idempotence, fill behavior (partial/full/none), and write-operation requirement. It complements the readOnlyHint=false and idempotentHint=false annotations, without contradiction.

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

  Conciseness5/5

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

  The description is four sentences, front-loaded with the core purpose. Every sentence earns its place, covering behavior, guidance, and prerequisites without redundancy. Highly concise and well-structured.

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

  Completeness5/5

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

  Given the tool's complexity (limit order, non-idempotent, write operation), the description covers all critical aspects: order type, fill behavior, state inspection, cancellation, validation, and required flag. It is complete and self-contained.

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

  Parameters4/5

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

  Schema coverage is 100%, but the description adds value by explaining the order type (GTC), pair rewrite rule (BTC to XBT), and validation hints (tick size, minimum volume). This extra context justifies a score above baseline 3.

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

  Purpose5/5

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

  The description clearly states the tool places a new GTC limit order on Luno, distinguishing it from sibling tools like list_orders and cancel_order. The verb 'place' and resource 'limit order' are specific, and the detailed behavior of partial/full fills further clarifies purpose.

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

  Usage Guidelines5/5

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

  The description explicitly tells when to use this tool (placing a limit order), when not to (use list_orders for state, cancel_order to withdraw), and suggests a prerequisite (get_markets_info for validation). It also notes the require write flag, providing complete usage context.

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

• get_markets_infoA
  4.9/5.0
  Behavior5/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. Description adds that it is a public endpoint with no auth required, enhancing transparency beyond annotations.

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

  Conciseness5/5

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

  Two sentences, front-loaded with purpose and key information, zero waste. Every sentence adds value.

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

  Completeness5/5

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

  Given output schema exists and annotations are rich, the description covers purpose, usage, parameter, and sibling differentiation. Fully complete for a list endpoint.

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

  Parameters4/5

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

  Schema has 100% coverage with description for the sole parameter 'pair'. Description explains it is optional, comma-separated, and filters results, adding value over the schema.

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

  Purpose5/5

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

  Description clearly states 'List supported Luno markets and their trading parameters', which is a specific verb+resource, and distinguishes from get_ticker for live prices.

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

  Usage Guidelines5/5

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

  Explicitly says 'Use this before placing an order to validate price/volume... not for live prices (use get_ticker)', providing clear when-to-use and alternative.

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

• get_tickersA
  5/5.0
  Behavior5/5

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

  Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds that the endpoint is public and no auth required, and explains the fields included in each ticker (last trade price, best bid, best ask, 24h volume), providing beyond-annotation context.

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

  Conciseness5/5

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

  The description is two sentences, front-loaded with the core functionality, and each sentence adds specific value: first states purpose, second covers output, use case, and alternative. No wasted words.

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

  Completeness5/5

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

  Given that an output schema exists and annotations are provided, the description covers input parameter usage, output fields, comparison with sibling, and authentication requirements, making it fully complete for an AI agent.

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

  Parameters5/5

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

  Schema description coverage is 100% for the only parameter 'pair'. The description elaborates on the format ('comma-separated list'), gives an example, and clarifies behavior when omitted ('return every supported pair'), adding value beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool lists the latest tickers for all Luno trading pairs or a subset, using the specific verb 'list' and resource 'tickers'. It distinguishes from the sibling tool get_ticker by noting the use case for multiple vs. single pair.

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

  Usage Guidelines5/5

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

  The description explicitly tells when to use this tool ('survey or compare multiple markets in one call') and when to use the alternative get_ticker ('when you only need a single pair'). It also notes that it is a public endpoint with no auth required.

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