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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Close') but doesn't clarify if this is a destructive mutation, requires specific permissions, has side effects (e.g., affecting account balance), or what happens on success/failure. This leaves significant gaps for a tool that likely modifies state.

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, efficient sentence with zero waste—it directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.

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 complexity of a likely state-modifying operation (closing a position), the description is incomplete. With no annotations, no output schema, and minimal behavioral context, it fails to address key aspects like what the tool returns, error conditions, or dependencies on other tools (e.g., needing an open position from 'get_positions').

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, with the 'ticket' parameter documented as 'Position ticket number'. The description doesn't add any meaning beyond this, such as explaining what a ticket number is or where to find it. The baseline score of 3 is appropriate since the schema does the heavy lifting.

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 action ('Close') and target ('an open position'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'get_positions' or 'place_order' in terms of when to use each, which prevents a perfect score.

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 no guidance on when to use this tool versus alternatives like 'place_order' (which might handle closing) or 'get_positions' (which lists positions). There's no mention of prerequisites, such as needing an open position to close, or exclusions for when not to use it.

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?

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It states the tool compiles and returns results but doesn't disclose critical traits like whether it's a read-only or mutating operation, potential side effects (e.g., file modifications), error handling, or performance considerations (e.g., compilation time).

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, efficient sentence that directly states the tool's function without unnecessary words. It is appropriately sized and front-loaded, making it easy to grasp quickly.

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 complexity of a compilation tool with no annotations and no output schema, the description is insufficient. It lacks details on what compilation entails (e.g., source code processing, error reporting), the format of results, or how it integrates with other tools like 'run_backtest', leaving significant gaps for an AI 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?

The input schema has 100% description coverage, clearly documenting the single parameter 'ea_name' with its type and format. The description adds no additional parameter semantics beyond implying compilation involves an EA, so it meets the baseline of 3 without compensating for any gaps.

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 action ('Compile') and resource ('an EA on MetaTrader 4') with the outcome ('get compilation results'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'sync_ea' or 'sync_ea_from_file' which might involve similar EA-related operations, preventing a perfect score.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., if the EA must exist locally), exclusions, or how it relates to siblings like 'list_local_eas' or 'run_backtest', leaving usage context unclear.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states this is a 'Get' operation, implying read-only behavior, but doesn't specify whether it requires authentication, has rate limits, returns real-time or cached data, or what format the information is in. This leaves significant gaps for a tool that retrieves account data.

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, efficient sentence that directly states the tool's purpose without any unnecessary words. It's front-loaded and wastes no space, making it highly concise and well-structured.

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 complexity of retrieving account information in a trading context, the description is inadequate. With no annotations, no output schema, and no details on what specific information is returned (e.g., balance, equity, margin), the agent lacks sufficient context to use this tool effectively compared to siblings.

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 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add any parameter details, which is appropriate here, but since there are no parameters to explain, it doesn't fully compensate for any gaps, so it scores just below the maximum.

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 verb ('Get') and resource ('MetaTrader 4 account information'), making the purpose unambiguous. However, it doesn't distinguish this tool from potential siblings like 'get_positions' or 'get_history', which might also retrieve account-related data, so it doesn't reach the highest score.

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 no guidance on when to use this tool versus alternatives. With siblings like 'get_positions' and 'get_history' that might overlap in retrieving account-related information, there's no indication of context, prerequisites, or exclusions for usage.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves results but does not describe key behaviors: whether it returns only the most recent backtest, if it requires authentication, potential rate limits, or error conditions. The description is too minimal to inform safe and effective use.

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, concise sentence that directly states the tool's function without unnecessary words. It is front-loaded and efficient, though it could be more structured by including key usage details. The brevity is appropriate but borders on under-specification.

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 complexity of backtesting tools and the lack of annotations and output schema, the description is incomplete. It does not explain what 'results' include (e.g., summary statistics, charts), how it relates to sibling tools, or behavioral aspects like idempotency. For a tool that likely returns critical financial data, this leaves significant gaps for an AI 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?

The input schema has 100% description coverage, with one parameter ('detailed') fully documented in the schema. The description adds no parameter semantics beyond what the schema provides (e.g., it does not clarify what 'last backtest' means in relation to the parameter). With high schema coverage, the baseline score of 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 states the tool's purpose ('Get results from the last backtest'), which is clear but vague. It specifies the verb ('Get') and resource ('results from the last backtest'), but does not distinguish it from sibling tools like 'get_backtest_status' or explain what constitutes 'results' (e.g., performance metrics, trade logs). This leaves ambiguity about the exact output.

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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., that a backtest must have been run first), exclusions, or comparisons to sibling tools like 'get_backtest_status' or 'run_backtest'. This lack of context makes it unclear when this tool is appropriate.

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?

With no annotations provided, the description carries full burden but only states it retrieves status without behavioral details. It doesn't disclose whether this is read-only (implied but not explicit), if it requires authentication, rate limits, error handling, or what happens if no backtest is running. The description is minimal and lacks critical operational 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?

The description is a single, direct sentence with no wasted words. It front-loads the core purpose ('Get the current status') efficiently. Every word earns its place, making it highly concise and well-structured for its simplicity.

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 annotations, no output schema, and a simple zero-parameter tool, the description is incomplete. It doesn't explain what 'status' returns (e.g., a string, object, or progress indicator), error conditions, or how it interacts with siblings like 'run_backtest'. For a tool in a backtesting context, more operational detail would help the agent use it correctly.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here. Baseline is 4 for zero parameters, as the schema fully covers the absence of inputs.

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 action ('Get') and target ('current status of a running backtest'), making the purpose evident. It distinguishes from siblings like 'get_backtest_results' by focusing on status rather than results. However, it doesn't specify what 'status' entails (e.g., progress percentage, error state), leaving some ambiguity.

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 when a backtest is running, but provides no explicit guidance on when to use this versus alternatives like 'get_backtest_results' or 'run_backtest'. No prerequisites (e.g., needing a backtest ID) or exclusions are mentioned, leaving the agent to infer context from tool names alone.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure but offers no information beyond the basic action. It doesn't describe whether this is a read-only operation, what data format is returned, if there are rate limits, authentication needs, or any side effects, making it inadequate for a tool with potential complexity.

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?

While concise with just three words, the description is under-specified rather than efficiently structured. It lacks front-loaded critical information and fails to earn its place by adding value beyond the tool name, making it ineffective despite its brevity.

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 annotations and no output schema, the description is incomplete for a tool that retrieves trading history. It doesn't explain what 'trading history' entails (e.g., transactions, orders, performance), the return format, or any behavioral traits, leaving significant gaps for the agent to infer.

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, with the 'days' parameter clearly documented as 'Number of days to look back' with a default of 7. The description adds no additional meaning beyond what the schema provides, so it meets the baseline of 3 where the schema does the heavy lifting.

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 'Get trading history' is a tautology that merely restates the tool name 'get_history' with minimal elaboration. It specifies the resource ('trading history') but lacks a clear, specific verb beyond 'get' and doesn't differentiate from sibling tools like 'get_account_info' or 'get_positions' that also retrieve trading-related 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 provides no guidance on when to use this tool versus alternatives. It doesn't mention context, prerequisites, or exclusions, and fails to reference sibling tools like 'get_account_info' for account details or 'get_positions' for current positions, leaving the agent with no usage direction.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves 'current market data' but doesn't specify what that includes (e.g., price, volume, bid/ask), latency, rate limits, authentication needs, or error handling. This leaves significant gaps for an agent to understand how the tool behaves in practice.

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, efficient sentence that front-loads the core functionality ('Get current market data') without unnecessary words. Every part of the sentence contributes directly to understanding the tool's 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 the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'market data' entails (e.g., structured fields like price or time), potential errors, or how results are returned. For a tool in a financial trading context with siblings that handle similar data, more context is needed to ensure proper usage.

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, with the 'symbol' parameter clearly documented as a trading symbol with examples. The description adds no additional parameter semantics beyond what the schema provides, such as format constraints or validation rules, so it meets the baseline for high schema coverage.

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 verb ('Get') and resource ('current market data for a symbol'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_history' or 'get_backtest_results', which might also retrieve market-related data but with different scopes or timeframes.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether the symbol must be active or subscribed), exclusions, or comparisons to siblings like 'get_history' (which might retrieve historical data) or 'get_positions' (which might show current holdings).

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Get all open positions' implies a read operation but doesn't specify whether this requires authentication, returns real-time or cached data, includes pagination, or handles errors. For a tool with zero annotation coverage, this leaves significant behavioral gaps.

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 perfectly concise at three words: 'Get all open positions.' It's front-loaded with the core action and resource, contains zero wasted words, and efficiently communicates the essential purpose without unnecessary elaboration.

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-parameter read tool with no output schema, the description is minimally adequate but leaves important context gaps. It doesn't specify what 'open positions' means in this domain (trading/financial context suggested by sibling tools), what format the data returns, or whether there are any constraints on usage. The description meets basic requirements but could be more 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 tool has zero parameters with 100% schema description coverage, so the schema already fully documents the parameter situation. The description doesn't need to compensate for any parameter gaps, and it appropriately doesn't mention parameters that don't exist. A baseline of 4 is appropriate for zero-parameter tools.

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 'Get all open positions' clearly states the verb ('Get') and resource ('open positions'), making the tool's purpose immediately understandable. However, it doesn't distinguish this from potential sibling tools like 'get_account_info' or 'get_history' that might also retrieve position-related data, preventing a perfect score.

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 no guidance on when to use this tool versus alternatives. With siblings like 'get_account_info' and 'get_history' that might overlap in retrieving position data, there's no indication of when this specific tool is appropriate or what distinguishes it from other retrieval operations.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists items but doesn't describe what 'available' means (e.g., remote vs. local, filtered by permissions), whether it's paginated, or what the output format looks like. This leaves significant gaps for a tool with zero annotation coverage.

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, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy to parse quickly.

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 lack of annotations and output schema, the description is incomplete. It doesn't explain what 'available' entails, how results are returned, or any behavioral traits like rate limits or permissions. For a tool with no structured data support, this minimal description leaves too many contextual 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?

The tool has zero parameters, and the schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, but it could have mentioned any implicit filters or scopes (e.g., by user or status). Baseline for zero parameters is 4, as it's inherently complete in this dimension.

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 action ('List') and resource ('available Expert Advisors for backtesting'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling tool 'list_local_eas', which appears to be a similar listing function, preventing a perfect score.

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 no guidance on when to use this tool versus alternatives like 'list_local_eas' or other sibling tools. It lacks context about prerequisites, timing, or exclusions, leaving the agent with minimal usage direction.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('List') but doesn't describe what 'List' entails (e.g., format of returned data, pagination, error handling, or whether it's a read-only operation). For a tool with zero annotation coverage, this is a significant gap in 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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, with no wasted information, making it easy for an agent to parse quickly.

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 lack of annotations and output schema, the description is incomplete. It doesn't explain what 'EAs' are, what data is returned, or how the listing behaves, leaving gaps in understanding for a tool that interacts with local development resources. More context is needed for adequate completeness.

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, with the single parameter 'folder' fully documented (including enum values and default). The description doesn't add any parameter details beyond what the schema provides, so it meets the baseline score of 3 for high schema coverage without extra value.

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 verb ('List') and resource ('EAs in the local development folders'), providing a specific action and target. However, it doesn't distinguish this tool from sibling tools like 'list_experts' or explain what differentiates 'EAs' from 'experts' in this context, preventing a perfect score.

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 no guidance on when to use this tool versus alternatives like 'list_experts' or other sibling tools. It mentions 'local development folders' but doesn't specify use cases, prerequisites, or exclusions, leaving the agent with minimal contextual direction.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure but offers minimal information. It states the tool places an order, implying a write/mutation operation, but doesn't cover critical aspects like authentication requirements, rate limits, error handling, or what happens on success/failure (e.g., order confirmation). This leaves significant gaps for a trading tool.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded with the core action, making it easy to parse, and every part of the sentence contributes essential information, earning a top score for conciseness.

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 complexity of a trading order tool with no annotations and no output schema, the description is insufficient. It lacks details on behavioral traits (e.g., side effects, error cases), usage context, and expected outcomes, which are critical for safe and effective tool invocation in a financial trading environment.

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%, providing clear documentation for all 7 parameters, so the description doesn't need to add parameter details. The description doesn't provide additional semantic context beyond the schema, such as explaining parameter interactions (e.g., 'price' is only for pending orders as noted in schema) or trading conventions, meeting the baseline for high schema coverage.

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 action ('Place') and resource ('a trading order in MetaTrader 4'), making the purpose immediately understandable. However, it doesn't distinguish this tool from its siblings like 'close_position' or 'get_positions' beyond the basic verb, which would require more specific differentiation for a perfect score.

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. For example, it doesn't mention prerequisites like account connection status, or contrast with sibling tools like 'close_position' for exiting trades or 'get_positions' for viewing open orders, leaving the agent without contextual usage cues.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Run a backtest') but doesn't explain what happens during execution—such as whether it's synchronous/asynchronous, how long it might take, error handling, or what output to expect. This is a significant gap for a complex operation with 9 parameters.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to understand at a glance.

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 complex tool with 9 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain the backtesting process, result format, error conditions, or how it relates to sibling tools. More context is needed to help an agent use this tool effectively.

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 schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema, such as explaining interactions between parameters or providing usage examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 verb 'Run' and the resource 'backtest on an Expert Advisor', providing a specific action. However, it doesn't differentiate from sibling tools like 'get_backtest_results' or 'get_backtest_status', which are related but distinct operations.

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 like 'get_backtest_results' or 'get_backtest_status'. The description lacks context about prerequisites, such as needing a compiled Expert Advisor or historical data availability.

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?

With no annotations provided, the description carries full burden for behavioral disclosure. While 'upload' implies a write operation, it doesn't specify whether this requires authentication, what happens if the EA already exists, whether compilation is automatic, or what the expected outcome is. The description lacks critical behavioral context for a tool that modifies system state.

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, efficient sentence with zero wasted words. It's appropriately sized for a tool with two parameters and gets straight to the point without unnecessary elaboration.

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 that uploads and potentially compiles code (a write operation with system impact), the description is insufficient. With no annotations, no output schema, and minimal behavioral disclosure, it leaves critical gaps about authentication requirements, error conditions, compilation process, and expected outcomes that an agent would need to use this tool effectively.

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 description coverage, the input schema already fully documents both parameters. The description adds no additional parameter semantics beyond what's in the schema - it doesn't explain format requirements, constraints, or relationships between parameters that aren't already covered.

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 action ('Upload EA file') and target ('to MetaTrader 4 for compilation'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from its sibling tool 'sync_ea_from_file', which appears to handle a similar function with different input sources.

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 no guidance on when to use this tool versus alternatives like 'sync_ea_from_file' or 'compile_ea'. There's no mention of prerequisites, context requirements, or exclusion criteria for tool selection.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'sync' but does not explain what this entails—whether it overwrites, updates, or merges data, or if it requires specific permissions or has side effects. This leaves key behavioral traits unspecified.

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, direct sentence with no unnecessary words, making it highly concise and front-loaded. It efficiently communicates the core action without any fluff.

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 lack of annotations and output schema, the description is incomplete. It does not cover what 'sync' means operationally, what happens on success or error, or how it interacts with MetaTrader 4, leaving significant gaps in understanding for a tool that performs a potentially complex operation.

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, so the parameters are well-documented there. The description does not add any additional meaning beyond the schema, such as explaining the sync process or file format requirements, but the schema provides adequate baseline information.

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 action ('sync') and the resource ('an existing EA file to MetaTrader 4'), making the purpose understandable. However, it does not distinguish this tool from its sibling 'sync_ea', which might cause confusion about their differences.

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 like 'sync_ea' or 'compile_ea'. The description lacks context about prerequisites, such as needing an existing EA file or when this operation is appropriate, leaving usage unclear.

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