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

Annotations already declare safe read-only, idempotent, and open-world hints. The description adds valuable context beyond: default merged card behavior, allBoards option, and structure details (primary board, otherBoards, offExchange flag). 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.

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

The description is compact yet information-dense, front-loading the core purpose and proceeding logically through input, output details, and special cases. No redundant sentences.

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 tool's complexity (multiple input methods, instrument types, board logic, and no output schema), the description covers all essential aspects: how to use, what is returned per instrument type, board structure, and the allBoards option.

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% with descriptions for all 5 parameters. The description summarizes input (tickers/ISINs) and output fields but does not add significant meaning beyond the schema. 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?

The description clearly states the tool finds instrument cards by tickers or ISINs, listing extended fields. It distinguishes itself from siblings by stating 'Start here to resolve a ticker before other calls,' making its role as an entry point explicit.

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 provides explicit guidance to use this tool first to resolve tickers before other calls. While it doesn't contrast with alternatives like get_instruments_by_type, it establishes a clear usage context.

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, idempotentHint, and destructiveHint false, indicating safe, read-only, and predictable behavior. The description adds valuable behavioral details: the 1000-bar API cap, inline returning most recent trading bars with a truncated flag, and outputPath enabling full-history chunking with deduplication and progress. This significantly enhances 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.

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

The description is three sentences, front-loaded with 'OHLCV candles.' It efficiently covers key aspects without redundancy, earning its place with each sentence.

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 tool's complexity (7 parameters, no output schema), the description covers core behaviors: inline/full modes, timeframes, bond pricing. It omits the classCode resolution detail, but that is covered in the schema. Overall, it provides sufficient context for selection and use.

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 86% (6 of 7 parameters described). The description adds meaning by enumerating valid timeFrame values, explaining the inline vs outputPath behavior, and noting bond price quoting. For example, the timeFrame enum values are listed and the outputPath param's full-history capability is explained, which goes beyond the schema's description.

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 clearly states 'OHLCV candles' and lists supported timeframes, making the tool's purpose explicit. However, it does not explicitly differentiate from sibling tools like get_quotes or get_recent_trades, though the context of 'candles' versus 'quotes' provides implicit distinction.

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 explains two usage modes: inline for up to 1000 bars and with outputPath for full history, guiding when to use each. It also notes bond price quoting. However, it does not explicitly state when to prefer this tool over alternatives like get_quotes.

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 indicate readOnly, idempotent, and not destructive. The description adds key behavioral details: only discountLong is exposed (no short rates), values are raw BCS coefficients, and tickers filter is applied client-side. This goes 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.

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

Three sentences, front-loaded with purpose, then behavioral caveats, then filter behavior. No wasted words.

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 read-only nature and schema coverage, the description explains the data source and important caveats. However, it does not describe the return structure or what a typical response looks like, which would be helpful since there is no output schema.

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 adds value by clarifying that the 'tickers' filter is applied client-side, which is not in the schema. No additional insight for 'outputPath' or 'outputFormat'.

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 clearly states it provides margin discount rates per instrument from the marginal-indicators service. While it doesn't explicitly distinguish from sibling tools, the verb 'get' and resource 'discounts' make the purpose clear.

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 warns that values may be unreliable ('observed as 1 for every instrument, so verify against the web cabinet'), implying caution. However, it lacks explicit when-to-use or when-not-to-use guidance, nor does it mention 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?

Beyond annotations (readOnly, idempotent, openWorld), description adds pagination limits (max 100 per page), outputPath behavior (fetches all pages, returns summary), and conditional parameter 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.

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

Two sentences with no waste. First sentence defines core function and pagination. Second adds key usage details. Front-loaded critical 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?

Covers pagination, bulk mode, conditional parameter, and type enum. No output schema but not needed. Sufficient for correct usage and selection among siblings. Minor missing detail about return format when not using outputPath.

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%, but description adds value: explains outputPath's effect on pagination and response format, and specifies baseAssetTicker's role for OPTIONS. Enhances understanding beyond schema.

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 clearly states it retrieves 'tradable instruments of a type' with pagination, using specific verb and resource. It distinguishes from siblings like 'find_instrument' by focusing on type-based filtering.

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?

Provides guidance on when to use outputPath for bulk fetching and notes baseAssetTicker requirement for OPTIONS. Lacks explicit comparison to sibling tools like 'find_instrument' but covers key usage contexts.

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 indicate read-only, non-destructive, and idempotent behavior. The description adds valuable behavioral details: it's a start-of-day snapshot in a single T365 slice, not intraday, and hides zero rows by default. This goes beyond annotations by clarifying the temporal and filtering 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?

The description is concise at two sentences, front-loading the main purpose and key behavioral notes. Every sentence adds useful information without redundancy or unnecessary detail.

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 tool's complexity (money limits, securities, futures) and lack of output schema, the description covers the main elements (freeByCurrency, loadDate) and flags important behaviors (zero rows, snapshot nature). It allows an agent to understand the scope and data limitations, though it doesn't detail output structure.

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 parameters are well-documented in the schema. The description adds value by explaining the includeZero parameter's effect (hiding zero rows), which aligns with the schema description. However, it does not add new meaning beyond what the schema provides for outputPath and outputFormat.

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 clearly states the tool retrieves account limits including money limits, securities, and futures. It differentiates from sibling tools like get_portfolio by specifying the exact types of limits. The verb 'get' implies retrieval, and the resource 'limits' is explicit. However, it doesn't explicitly contrast with siblings for usage.

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 notes that the API returns a start-of-day snapshot (not intraday) and that zero rows are hidden unless includeZero=true. This provides context but does not give explicit guidance on when to use this tool versus alternatives like get_portfolio. It implies usage for limit inquiries but lacks when-not-to-use or alternative suggestions.

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 indicate read-safe, idempotent, non-destructive behavior. The description adds useful behavioral context: bond price quoting convention and the potential 404 error. 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.

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

The description is very concise with three sentences, each providing essential information. No filler or redundancy. Front-loaded with the core purpose.

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 no output schema, the description adequately covers return contents (bids/asks with prices, quantities, total volumes) and important edge cases (bond pricing, 404 error). Could mention depth level or pagination, but overall sufficient for this tool.

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 description does not need to add parameter meaning. The description adds no additional parameter context beyond schema, but the baseline is 3.

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 clearly states the tool retrieves an order book (L2 depth of market) for one instrument, listing specific data (bids/asks, prices, quantities, total volumes). This is distinct from siblings like get_quotes (top of book) or get_candles (historical prices).

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 provides some usage context, noting that bond prices are in % of face value and that the API may return 404 outside trading sessions. However, it does not explicitly state when to use this tool over alternatives or provide prerequisites.

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?

Disclosures beyond annotations include temporal scope (data since 2026-01-26), pagination behavior, file dumping with outputPath, and the absence of rejected orders. No contradiction 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.

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

Extremely concise: two sentences plus a parenthetical, each sentence provides essential information. Front-loaded with core purpose.

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?

Despite 7 parameters and no output schema, the description covers all key aspects: data returned, filtering, pagination, file dumping, and limitations. No gaps.

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?

Adds significant meaning beyond schema: explains that page is ignored with outputPath, that outputFormat defaults based on file extension, and describes outputPath behavior with a concrete response structure example.

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 clearly states that the tool lists orders with specific fields (ticker, side, type, etc.) and includes a data range. It distinguishes from sibling tool get_order_status by noting that rejected orders are not shown here.

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 tells when to use (to get orders) and when not to (rejected orders), providing the alternative tool get_order_status. Also explains use of outputPath for bulk data.

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. The description adds the mapping for orderIdType, but does not disclose what happens if the order is not found, rate limits, or any error behavior. The additional behavioral insight is minimal.

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 that are front-loaded with the core purpose. Every word adds value; no extraneous content. Efficient and clear.

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 simple read-only tool with 4 parameters and no output schema, the description covers the essential mapping for orderIdType. However, it lacks details about the return value structure and error handling, which would be helpful for an agent.

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 baseline is 3. The description adds value by elaborating on the orderIdType parameter with concrete examples and format explanation, which goes beyond the schema's brief enum descriptions.

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 clearly states that the tool retrieves the status of a single order by ID, and it distinguishes itself from sibling tools like get_orders (which lists orders) and get_recent_trades (different data). It also explains the two order ID types with an example.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., get_orders or get_recent_trades). There is no mention of prerequisites or conditions that would make this tool appropriate or inappropriate.

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, etc. The description adds behavioral details about settlement slices, duplicate handling, and csv output, which go beyond 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.

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

The description is informative but slightly verbose; it front-loads the main purpose but includes some explanatory details that could be streamlined. Still effective overall.

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?

Despite no output schema, the description thoroughly explains the return structure (positions, prices, P&L, totals by type) and covers edge cases like duplicate slices, making it complete for the tool's complexity.

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?

Input schema has 100% coverage with descriptions. The description adds context on term=all's effect on totals and csv output format, providing extra meaning beyond the schema.

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 clearly states the tool retrieves the portfolio of the account bound to the token, listing positions with financial details. It distinguishes from sibling tools like get_limits or get_trades, which serve different purposes.

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 explains the term parameter behavior (default single slice vs term=all duplicates) but does not explicitly guide when to use this tool over alternatives like get_trades or get_limits. It lacks when-not-to-use 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 mark the tool as readOnly and idempotent. The description adds important behavioral context: real-time nature, 100-instrument limit, bond prices quoted as % of face value, and automatic classCode resolution via find_instrument. This goes beyond what annotations provide, though it does not mention pagination or outputPath 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?

The description consists of 3 concise sentences that front-load the core purpose and key data points. It avoids unnecessary words and jargon. Minor improvement possible by mentioning outputPath, but it remains efficient.

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 no output schema and 4 parameters, the description covers the returned data, bond pricing nuance, and a cross-reference to get_portfolio. However, it does not explain the optional outputPath and outputFormat parameters, which are documented in the schema but not integrated into the description's narrative. Adequate but not fully complete.

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 input schema has 100% description coverage for all 4 parameters. The description adds minimal value beyond the schema; it mentions classCode auto-resolution but does not elaborate on outputPath or outputFormat. Baseline 3 is appropriate since the schema already documents the parameters well.

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 clearly states the tool provides real-time quotes for up to 100 instruments, listing specific data points (bid/offer, last price, day open/close/high/low, change). It distinguishes itself from siblings by noting that get_portfolio already carries currentPrice for user positions, and mentions classCode resolution via find_instrument, clarifying its relationship to that sibling.

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 provides clear context for when to use the tool (for real-time quotes). It explicitly tells users not to use it for their own portfolio's current price, directing them to get_portfolio instead. While it does not exhaustively list alternatives, the guidance is sufficient for the common case.

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?

The description adds behavioral details beyond the annotations, such as the absence of trade IDs, clamping behavior, bond pricing in % of face value, and hour-by-hour fetching. It does not contradict any annotation.

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 description is relatively lengthy but all sentences add value. It is front-loaded with the core purpose and then covers important details. A minor reduction could be made without losing essential 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?

Given the number of parameters, backend constraints, and file output feature, the description covers most aspects: date restrictions, limit behavior, outputPath semantics, and bonds pricing. It lacks an explicit mention of inline return structure but the summary and sample are implied.

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?

With 100% schema coverage, the description adds value by explaining nuances: from clamping, limit ignored with outputPath, outputPath behavior, classCode resolution via find_instrument, and outputFormat details. This goes beyond mere schema descriptions.

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 clearly identifies the tool as an anonymized recent trades feed for a single instrument, specifying the verb ('get') and resource ('recent trades') and enumerating the data fields. It distinguishes itself from siblings like get_trades by mentioning 'anonymized' and focusing on recent trades.

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?

Provides explicit guidance on when to use and important constraints: the API serves only current UTC day, hour-by-hour fetching, backend caps, and the effect of outputPath. It does not explicitly state alternatives or when not to use, but the context is clear enough for an agent to decide.

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 indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context: 'No broker API calls, never includes tokens', which goes beyond the annotations and discloses important safety guarantees.

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 description is a single, well-structured sentence. It front-loads the purpose ('Server diagnostics for support/feedback reports') and includes all necessary information without waste.

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 no parameters, no output schema, and annotations covering safety, the description provides a complete overview of what the tool returns and what it avoids. It leaves no gaps for a simple diagnostics tool.

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?

There are no parameters, so schema coverage is 100%. The description does not need to compensate, and a baseline of 4 is appropriate since the tool requires no input.

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 clearly states that the tool returns server diagnostics (version, runtime, mode flags, output root) and explicitly mentions what it does not include (tokens) and that it makes no broker API calls. This is specific and distinguishes it from sibling tools.

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 provides a clear use case: 'for support/feedback reports'. It does not explicitly mention when not to use or alternatives, but no sibling tool performs a similar function, so the context is sufficient.

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 destructiveHint=false, so the agent knows it's safe. The description adds that only executed trades are returned, data starts from 2026-01-26, and that outputPath fetches all pages. 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.

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

The description is extremely concise—two sentences covering purpose, available fields, pagination, filters, outputPath behavior, and a caveat about cash operations. No wasted words.

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 there is no output schema, the description adequately explains the return structure (fields listed) and the outputPath summary format. It also covers all key usage aspects: pagination, filters, file output, and data scope. Complete for an agent to invoke 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% with clear descriptions. The tool description adds value by explaining that page is ignored when outputPath is used, and that outputFormat can be inferred from file extension. This goes beyond the schema's individual param descriptions.

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 clearly states the tool retrieves executed trades on the account, listing specific fields (ticker, side, quantity, etc.) and noting that cash operations are excluded, making the purpose unambiguous and distinguishing it from siblings like get_recent_trades.

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 explains pagination with page/size, optional date and ticker filters, and the outputPath mechanism for bulk data dumping. It also clarifies that trades only are returned, not cash operations, giving context on scope. However, it does not explicitly contrast with sibling tools like get_recent_trades.

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 the tool as read-only and idempotent. The description adds behavioral context: times are in MSK (+03:00), results are sorted, and intervals with tradingSessionStatus=OPEN indicate active trading. This supplements annotations well.

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 with no wasted words. First sentence summarizes purpose and key details (timezone, sorting). Second sentence explains the critical status field. Efficient and 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?

Given no output schema, the description adequately covers what is returned (session types, times, sorted, status meaning). Minor gap: lack of explicit return structure, but sufficient for effective use.

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% (all 4 parameters described). The description adds no extra meaning beyond the schema, so 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?

The description clearly states the tool provides trading sessions for an instrument for the current day, including session types, start/end times in MSK, and sorted order. This specific verb+resource distinguishes it from siblings like get_trading_status (current status) and get_candles (price data).

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 implies usage for retrieving daily trading schedules but does not explicitly state when to use this tool vs alternatives, nor provide exclusion criteria. The context is clear but lacks explicit 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?

Beyond the readOnly and idempotent annotations, the description discloses cross-checking behavior, warning field addition, and a known upstream bug where CLOSE is reported during open evening sessions. This adds significant transparency.

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 description is concise (2-3 sentences), front-loads the main purpose, and every sentence adds unique value, including the observed bug note.

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 tool with 4 parameters and no output schema, the description adequately explains the return structure (session type, open/close, next change time, warning fields) and the cross-check logic. The known bug adds completeness. Minor gap: does not mention potential pagination or limits.

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 descriptions already cover all 4 parameters with 100% coverage. The description does not add new semantics beyond what is already in the schema, meeting the 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?

The description clearly states the tool returns current trading session status per instrument, including session type, open/close status, and time of next change. It also mentions cross-checking against schedule, distinguishing it from related tools like get_trading_schedule.

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?

No explicit guidance on when to use this tool versus alternatives like get_trading_schedule. The description implies it provides detailed status with cross-checking, but does not state when this is necessary or when to avoid it.

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