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

Discloses browser opening, automatic token saving, scope hierarchy, and error behavior. Without annotations, this covers key behavioral traits well, though token persistence details could be added.

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?

Concise with no wasted words; information is front-loaded. Slight structural improvement possible (e.g., separating flow and scope advice) but still highly 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?

For a simple auth tool with one parameter and no output schema, the description covers flow, scopes, error handling, and relative to siblings, it is 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 parameter 'scope' is fully covered by schema, and description adds valuable context: explains each scope meaning, hierarchy, and usage advice, exceeding schema info.

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 logs in via browser, opens a login page, saves token, and explains scopes. It distinguishes from siblings by describing the OAuth flow vs. other auth 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?

Explicitly advises 'pick paper first' for safe defaults, and explains error handling (403 insufficient_scope). Provides clear when-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?

No annotations provided, so description carries full burden. It discloses caching (30s per token) and lists exact return fields (user, scopes, capabilities, balance, client info). It does not mention side effects, but as a read-only check this is acceptable. Could be slightly more explicit about non-destructiveness.

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

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

Front-loaded with primary purpose, then detailed bullet-like list. Every sentence adds information; no wasted words. Efficiently communicates purpose, usage, and return data.

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 or annotations, the description covers all critical aspects: purpose, when to use, return data, caching. Could explicitly reference sibling tools (e.g., 'for actual auth use authenticate or login'), but not required. Overall sufficient for agent decision-making.

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?

No parameters (0 params, 100% schema coverage). The description adds value by detailing what data is returned beyond the empty schema. Baseline for 0 params is 4; the description meets it by explaining output semantics.

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 'Preflight check before invoking other tools' and enumerates the returned data (authenticated user, OAuth scope, tier capabilities, wallet balance, client info). It distinguishes itself from siblings like 'authenticate' and 'login' by focusing on scope selection and cost awareness.

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?

Explicit guidance: 'Agents should call this at the start of a workflow to pick the narrowest scope needed and to surface cost/balance to the user before committing to a charge.' Also mentions caching behavior (30s), which helps the agent decide when to call.

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?

Description discloses that the tool executes a market order, which is a key behavioral trait beyond the lack of annotations. However, it omits other important details like irreversibility, required permissions, or post-close effects.

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 front-loading the main action and a critical warning. Every sentence provides essential information with no 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?

Despite the dangerous nature (market order), the description lacks details on expected outputs, error conditions, or prerequisites. An agent would need more context for safe 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% with descriptions for all parameters. The tool description adds no additional meaning or usage context to the parameters.

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 'Close an open trading position' uses a specific verb and resource, clearly stating the tool's function. It distinguishes itself from sibling tools like get_positions by indicating it performs an action rather than retrieval.

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 on when to use versus alternatives. The warning about market order execution gives some context but does not specify when not to use or mention alternative tools like limit orders.

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 bears the full burden. It only states 'compare side by side' but does not disclose whether the tool is read-only, modifies state, or has side effects. The constraint of 2-5 strategy IDs is present in the schema but not in the description.

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 sentence, concise and front-loaded. However, it could be more informative without adding length, e.g., mentioning the output format or key metrics.

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 low complexity, the description adequately states the purpose but lacks details on what 'key metrics' are and the output format. It is minimally sufficient but incomplete.

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%, and the description adds no extra meaning beyond what the parameter schema already provides. Baseline 3 is appropriate since the description does not enhance understanding of the 'ids' parameter.

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 compares multiple strategies on key metrics. However, it does not differentiate from siblings like 'suggest_strategies' or 'explain_strategy', missing an opportunity to clarify its unique role.

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 on when to use this tool versus alternatives such as 'suggest_strategies' or 'explain_strategy'. The agent is left to infer usage context without explicit exclusions or recommendations.

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, the description carries full behavioral burden. It discloses browser interaction and key security (keys never enter chat). However, it omits prerequisites (e.g., logged-in session), side effects (record creation), and post-action behavior (success message or error).

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, front-loaded purpose, no redundant words. Each sentence provides distinct value: first states action, second adds behavioral and security context.

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 zero parameters, no output schema, and no annotations, the description covers the essential flow. Missing post-connection behavior (e.g., success, next steps) but overall adequate for a simple interactive 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?

Input schema has no parameters (100% coverage). The description adds meaning beyond schema by explaining the process (browser page for key entry) and security guarantee. Since no parameters exist, description compensates 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 connects a new exchange account via browser for entering API keys. It distinguishes from siblings like authenticate (user auth) and create_paper_exchange (paper trading) by specifying 'exchange account' and 'via browser'.

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 vs alternatives like authenticate or create_paper_exchange. The description implies connection of a real exchange, but no prerequisites, conditions, or exclusion criteria are provided.

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?

Explains no API keys required, simulated balance, no real money. Discloses OAuth scope and session-cookie user access. No annotations provided, so description carries full burden; adequate but could mention rate limits or limits on number of exchanges.

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 paragraphs, front-loaded with purpose and key benefit. No redundant sentences. Efficiently conveys purpose, auth requirements, and usage context.

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?

Fairly complete for a creation tool. Could mention what the response contains (e.g., exchange ID, status) since no output schema exists, but the use case is clear enough for agent invocation.

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

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

Schema coverage is 100%. Description adds meaningful examples (e.g., 'binance' for platform, 'BTC Paper Test' for accountLabel) and clarifies enum values (spot vs futures). Justifies baseline 3 plus 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?

Clearly states it creates a paper-trading exchange with simulated balance. Distinguishes from siblings like connect_exchange (presumably live). Recommends for first-time users and paper workflows.

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?

Recommends as starting point for first-time users and paper workflows. Mentions auth scope requirements. Does not explicitly state when not to use or compare to alternatives, but context from sibling names implies connect_exchange for live.

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, the description only states basic creation behavior. It omits details about what happens during creation (e.g., validation, storage, side effects).

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, but it could be more informative without sacrificing 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?

Lacks explanation of 'TradeDroid code', no output schema, missing behavioral details, making it incomplete 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.

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

Schema coverage is only 60% (3 of 5 parameters have descriptions). The description adds no additional parameter semantics beyond repeating 'from TradeDroid code'.

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 creates a new trading strategy from TradeDroid code, which is specific and distinguishes it from sibling tools like generate_strategy or explain_strategy.

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 on when to use this tool vs alternatives such as generate_strategy, nor any conditions or prerequisites mentioned.

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, the description is the sole source of behavioral info. It discloses a key safety default (paper trading) but omits details about live mode behavior, authentication needs, or potential destructive outcomes.

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 that immediately conveys the tool's purpose and a critical safety detail. 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 the tool's complexity (8 parameters, no output schema), the description lacks information about return values, error conditions, or prerequisites. It does not tell the agent what happens upon successful deployment or what formats are returned.

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 63% (moderate). The description adds minimal extra meaning beyond the schema, only clarifying the live parameter's default. For parameters without schema descriptions (e.g., name, symbol), no additional context is provided.

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's action ('Deploy a strategy as a trading bot') and distinguishes it from sibling tools like stop_bot or list_bots. It also adds a key behavior (defaults to paper trading) that differentiates it from live deployments.

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 mentions a default safety behavior (paper trading) but provides no guidance on when to use this tool versus alternatives like create_strategy or what_if_backtest. It does not specify prerequisites or contraindications.

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 full burden. It discloses outputs (what it does, risk profile, market conditions) but does not mention any behavioral traits like no side effects, data freshness, or required permissions.

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

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

A single, concise sentence that is front-loaded with the main purpose and includes key details. 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?

For a simple tool with one parameter and no output schema, the description adequately covers purpose and outputs. Could be improved by mentioning that the explanation is generated or based on historical data, but it is already fairly 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?

Schema description coverage is 100% for the single 'id' parameter. The tool description adds no additional meaning beyond the schema's 'Strategy ID', 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 a 'plain-English explanation of a strategy' and specifies what it covers: functionality, risk profile, and best market conditions. This is specific and distinct from sibling tools like 'get_strategy' which likely returns raw 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 when to use (when an explanation is needed) but provides no explicit guidance on when not to use or alternatives among siblings like 'get_strategy' or 'compare_strategies'.

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 provided, but the description discloses the prerequisite (completed backtest) and output format (CSV and PDF download URLs). Lacks details on link expiration or auth needs, but is adequate for a simple 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?

Two sentences are concise, front-loaded with the purpose, and contain no unnecessary 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?

For a single-parameter tool with no output schema, the description covers the purpose, prerequisite, and output format adequately. Could mention link expiration or auth, but not essential.

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 provides 'Backtest ID' for the id parameter. Description does not add additional meaning beyond context, 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 'Get export links for a completed backtest' with a specific verb and resource, and distinguishes from siblings like get_backtest_results and export_bot_trades by focusing on export links.

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?

Implies the backtest must be completed, but provides no explicit guidance on when to use this tool versus related tools like get_backtest_results or export_bot_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?

No annotations are provided, so the description carries the full burden. It does not disclose side effects, file generation, permissions, or whether the tool is read-only. The term 'Export' may imply file download but is not clarified.

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. Front-loaded with the core action and follow-up on return content.

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

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

The description covers the basic purpose and return data but lacks details on output format, pagination, or any limitations. For a simple tool with no output schema, it is adequate but not thorough.

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 some context about returned data (PnL, prices, summary) but does not elaborate on parameter behavior beyond what the schema covers.

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 exports a bot's trade history as structured data, mentioning specific elements like PnL and prices. It distinguishes from siblings like export_backtest and get_trade_history, though not explicitly.

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

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

No guidance on when to use this tool versus alternatives such as get_trade_history or export_backtest. The description only states what the tool does without 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?

No annotations are provided, so the description must cover behavioral traits. It warns about capital commitment, which is key, but does not disclose other important details like reversibility, fees, or execution timing.

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 with one sentence plus a warning. Every word adds value, and the structure is clear 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 or annotations, the description provides the essential purpose and a critical behavioral warning. It is reasonably complete for a tool that commits capital, though more detail on the follow process would enhance 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?

Schema coverage is 100% and each parameter has a brief description. The tool description does not add extra semantic value beyond the schema, so 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 clearly states the action ('subscribe to copy') and the resource ('top trader's trades'), making the purpose unambiguous. It distinguishes itself from siblings by being the only tool focused on copying 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 warning 'commits capital' provides important usage context, but the description does not explicitly state when to use this tool versus alternatives (e.g., strategy creation tools) or 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?

No annotations provided, so description bears full burden. It states the tool generates a strategy but does not disclose side effects (e.g., whether the strategy is saved automatically), required permissions, or behavior on ambiguous input.

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

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

Two concise sentences that front-load the purpose and mechanism. Every word adds value with no redundancy.

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?

No output schema and no annotations, so description must cover return value and integration points. It omits what the generated code means, how to deploy it, and how this differs from manual strategy creation.

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 67% (2 of 3 params described), so baseline is 3. The description does not add any parameter details beyond what the schema provides (e.g., default values, enum options).

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?

Clearly states 'Generate a trading strategy' and distinguishes from siblings by specifying 'using AI' and 'natural language description'. The mention of 'AI creates the TradeDroid code' adds specificity about the 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?

No explicit guidance on when to use this tool versus alternatives like 'create_strategy' or 'suggest_strategies'. The description implies usage for natural language inputs but lacks when-not-to-use or comparison 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?

No annotations are provided, and the description only says 'Check status/results,' implying a read-only operation but not explicitly stating it is non-destructive or detailing any side effects.

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 with no wasted words, though it could benefit from slightly more detail on output or usage.

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 tool with one parameter and no output schema, the description is adequate but lacks details on the return format or potential statuses.

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 schema provides 100% coverage with a clear description for the sole parameter ('Backtest job ID'). The tool description adds no additional 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 verb 'check' and the resource 'status/results of a previously started backtest,' accurately distinguishing it from sibling tools like run_backtest or export_backtest.

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 phrase 'previously started' implies it should be used after initiating a backtest, but no explicit when-not or alternative tools are mentioned.

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 present, so the description carries full burden. It only states a read operation ('get') but does not disclose whether authentication is required, if there are any side effects, rate limits, or limitations. The minimal description provides insufficient behavioral insights for an agent.

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 sentence that front-loads the verb and resource. Every word is informative and no repetition or fluff exists.

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 is simple with one parameter and no output schema, the description should elaborate on the return value (e.g., fields like running state, last activity). It does not, leaving the agent unaware of what 'status and performance' entails, which is a notable gap.

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 covers the single parameter 'id' with description 'Bot ID' (100% coverage). The description adds no extra meaning beyond this, so baseline 3 is appropriate. No additional param explanation is needed.

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 detailed status and performance for a specific bot' clearly states the verb (get) and resource (status and performance for a specific bot), distinguishing it from sibling tools like list_bots or deploy_bot. However, it lacks specificity on what 'detailed status' includes, such as health metrics or running state.

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 usage context is provided. There is no indication of when to use this tool versus alternatives like list_bots (which might provide an overview) or other status-checking tools. No exclusions or prerequisites are mentioned.

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, the description carries the burden of behavioral disclosure. It only says 'get data' without stating any behavioral traits like rate limits, data ordering, or time range handling. Very minimal disclosure.

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 short (one sentence), which is concise but it lacks essential information. It is under-specified for a tool with 4 parameters and no output schema.

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 data retrieval tool with no output schema, the description should explain return values or data format. It also neglects to mention the meaning or constraints of the 'exchange' and 'limit' parameters. Incomplete.

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 only 25% (only 'symbol' has a description). The description does not add any meaning to other parameters like 'timeframe', 'limit', or 'exchange'. It fails to compensate for the low 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 the resource 'OHLCV candlestick data' for a trading pair. It is specific enough to convey the basic purpose, but does not distinguish from siblings like get_price or get_market_context.

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 on when to use this tool versus alternatives such as get_price (for current price) or get_market_context (for broader market data). The description lacks any contextual comparison.

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 only states that the tool retrieves market context but does not mention whether it is read-only, if authentication is required, what side effects exist, or how the outputs are computed. This is insufficient for safe invocation.

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 sentence that immediately fronts the key information: the tool's action and the three outputs. It contains no extraneous words and is efficiently 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?

The tool has no output schema, so the description should explain the return format. It lists three concepts but does not specify what form they take (e.g., numerical values, strings, objects). Also missing prerequisites (e.g., valid exchange connection) and error conditions.

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% (all three parameters have descriptions). The tool description adds no extra meaning beyond repeating the parameter names; it does not clarify value ranges, formatting, or relationships. Baseline 3 is appropriate given high 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 market context' and specifies the resource 'for a symbol'. It enumerates three outputs (trend direction, volatility level, support/resistance levels), which distinguishes it from sibling tools like get_candles (raw data) or get_price (single price).

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 such as get_candles or get_portfolio. No explicit context or exclusions are given, leaving the agent to infer appropriate use from the purpose 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?

No annotations provided, so the description must carry the full burden. It only lists metrics retrieved but omits details like authentication needs, whether calculations are real-time or cached, or how missing data is handled.

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?

Single sentence that is front-loaded with purpose. No unnecessary words, but could include more detail without being verbose.

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

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

With no output schema, the description should explain return values or metrics format. It mentions metric names but not structure, unit, or aggregation method. Incomplete for a metrics 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 schema fully describes parameters. The description adds no extra parameter information beyond listing metrics, which is already implied. 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 verb 'Get' and the resource 'trading performance metrics', listing specific metrics (ROI, win rate, PnL, Sortino ratio). This distinguishes it from sibling tools like get_portfolio or get_positions.

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 on when to use this tool vs alternatives, prerequisites, or when not to use it. With many sibling tools that could be related (e.g., get_strategy, get_backtest_results), this is a significant gap.

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 provided, so description carries full burden. Describes output but does not disclose if the operation requires authentication, has side effects, data freshness, or any behavioral traits beyond the mere retrieval.

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?

Single, well-structured sentence that front-loads the purpose and includes specific output details. Every word earns its place with no redundancy.

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, the description is adequate but not rich. Given no output schema, more detail on return structure or expected fields would improve completeness. Still meets minimum viability.

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?

No parameters (0), schema coverage 100% already reflects that. Description adds value by specifying what the output contains (balance, exchanges, active bots), which is beyond the empty 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?

Description clearly states verb 'Get' and resource 'portfolio overview', listing included components (balance, exchanges, active bots), distinguishing from siblings like get_bot_status or get_positions.

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 on when to use this tool versus alternatives. With many sibling tools (e.g., get_bot_status, get_performance_metrics), the description should indicate typical use cases or exclusion criteria.

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. It states it's a read operation but lacks behavioral traits such as permissions, rate limits, or response format details.

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 with no redundant words, efficiently conveying 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?

For a simple list tool with one optional parameter and no output schema, the description is adequate but lacks details on output format, pagination, or interpretation of 'current PnL'.

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 the 'exchange' parameter already described. The description adds no additional meaning beyond 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 verb 'Get' and resource 'open trading positions with current PnL', which is specific and distinguishes it from sibling tools like get_portfolio.

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

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

Usage is implied ('when you need open positions with PnL'), but no explicit comparison to alternatives like get_portfolio or get_trade_history, nor any 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?

No annotations are provided, so the description carries the full burden. It only states that it 'gets' the price, without disclosing whether the price is real-time, cached, or subject to rate limits. The behavioral implications of a read operation are not explicitly described.

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 with no unnecessary words. It efficiently communicates 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?

No output schema exists, but the description does not explain the return format (e.g., price as number, currency unit). It is adequate for a simple tool but leaves some ambiguity about what the agent will receive.

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%, and both parameters have basic descriptions. The description adds no additional meaning beyond the schema, only repeating the example BTC/USDT already present in the symbol parameter. 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 clearly states the tool retrieves the current price of a trading pair with an example. It uses a specific verb ('get') and resource ('price'), and among sibling tools like get_candles or get_market_context, it uniquely focuses on the current price.

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 on when to use this tool versus alternatives such as get_candles (historical data) or get_market_context (broader market info). The description does not mention prerequisites like authentication or exchange connection.

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, the description carries full burden but only states it gets info. No disclosure of authentication needs, error handling, or side effects. Minimal behavioral insight.

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 single sentence with no unnecessary words. Every element serves a 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?

For a simple read tool with one required parameter and no output schema, the description is minimally adequate but lacks details on return format, required auth, or error conditions. 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?

Schema coverage is 100% with a single parameter 'id' described as 'Strategy ID'. The description adds no extra meaning beyond what the schema provides, 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?

Description clearly states the tool retrieves detailed information about a specific strategy, using a specific verb and resource. It distinguishes from sibling tools like list_strategies and compare_strategies.

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 list_strategies for overviews or compare_strategies for comparisons. Missing context on prerequisites or conditions.

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 provided, so description must carry burden. Mentions output content but does not disclose authentication needs, side effects (read-only), rate limits, or behavior when no trades exist.

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?

Single sentence that is front-loaded with purpose and key data points. Efficient but lacks structure (e.g., bullet points or examples).

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?

No output schema and no annotations. Description is minimal and does not cover return format, pagination behavior, error handling, or edge cases given complexity of sibling tools.

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 3. Description adds no extra meaning beyond schema parameter descriptions. Does not elaborate on parameter usage or formatting.

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?

Clearly states the verb 'Get', resource 'closed trade history', and included data (PnL, entry/exit prices, duration). Distinguishes from sibling tools like get_positions.

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 (e.g., get_positions for open trades). No when-not-to-use or exclusions.

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?

Without annotations, the description implies a read-only listing operation but does not disclose authentication requirements, pagination behavior, or how performance is computed. The term 'list' suggests no side effects, but more detail is needed for full 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, clear sentence with no wasted words. It front-loads the action and key details, making it easy to scan.

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 tool with no parameters and no output schema, the description is adequate but could be improved by specifying what 'status' and 'performance' entail (e.g., returned fields). Given the low complexity, it meets minimum viability.

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 zero parameters in the schema, so schema coverage is trivially 100%. The description adds no additional parameter info, which is acceptable since there are none. A score of 3 reflects the baseline for high 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 (list), the resource (trading bots), and the scope (all your bots including status and performance). It effectively distinguishes from sibling tools like get_bot_status which target a single bot.

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 on when to use this tool versus alternatives such as get_bot_status or get_performance_metrics. The description does not specify any context, exclusions, or 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?

No annotations provided, so description bears full burden. It discloses the output fields (IDs, platform names, status) but does not explicitly state it is a read-only operation with no side effects. However, this is implied by 'list'.

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?

Single sentence, efficient, 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?

For a simple parameterless list tool with no output schema, the description adequately explains purpose and return fields. Complete for its 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?

No parameters, so description does not need to add meaning. Baseline 4 for zero parameters.

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 lists connected exchange accounts and specifies the output fields (IDs, platform names, status). Verb 'list' and resource 'exchange accounts' are specific.

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 when/when-not instructions or alternatives. Implied usage is obvious for listing connected accounts, but given siblings like 'check_auth' or 'connect_exchange', more guidance could help.

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, the description carries the full burden but only states the action without disclosing behavioral traits like side effects, authentication requirements, or data freshness. Minimal 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?

Single sentence, front-loaded with key verb and resource. No extraneous words; every element is essential.

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 listing tool with one optional parameter and no output schema, the description is adequate but lacks details on return format or ordering. Could be more complete given the number of sibling tools.

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% and the schema already describes the 'owned' parameter. The description adds no additional meaning beyond what the schema provides, so baseline score of 3 applies.

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

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

The description 'List available trading strategies' uses a specific verb ('list') and resource ('trading strategies'), clearly distinguishing it from sibling tools like 'get_strategy' or 'create_strategy'.

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 on when to use this tool versus alternatives such as 'suggest_strategies' or 'compare_strategies'. The context of when to list vs other operations is not provided.

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 must convey behavioral traits. It states 'Browse,' indicating a read-only operation, and provides no hints of destructive actions or auth requirements. The description is adequate but does not fully disclose scope or side effects, earning a mid-range score.

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 conveys the core functionality without any unnecessary words. It is well-structured and immediately understandable.

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 simplicity of the tool (3 optional parameters, no output schema), the description is nearly complete. It clearly communicates the overall function. However, it could briefly mention the returned data structure or the nature of the leaderboard, but this is a minor gap.

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 covers 100% of parameters with descriptions, so the description adds no additional meaning beyond the schema. The tool's description does not elaborate on parameter usage beyond what is already in the schema, resulting in a baseline score of 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's purpose: to browse a leaderboard of top-performing traders for copying. It uses specific verbs ('Browse') and resource ('leaderboard of top-performing traders'), and implicitly distinguishes from sibling tools like 'list_bots' or 'list_exchanges'.

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 finding traders to copy but does not explicitly state when to use this tool vs. alternatives (e.g., 'search_markets' or 'follow_trader'). No exclusions or prerequisites are mentioned. It meets the minimum viability 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?

No annotations exist, so the description must disclose side effects. It only says 'log in' without mentioning token issuance, session creation, or potential rate limits. Security implications are omitted.

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 single sentence. Front-loaded with purpose, but could add more value without verbosity.

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?

Adequate for a simple authentication tool with fully described parameters. Lacks expected output description (e.g., token) and error handling guidance.

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 for both parameters exist (email and password). The description adds no extra meaning; baseline of 3 is appropriate given 100% 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?

Description clearly states the action (log in) and the resource (TradeStaq) with required credentials (email and password). It is specific and distinct from siblings like 'authenticate' and 'logout'.

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 on when to use this tool versus alternatives like 'authenticate', nor any prerequisites (e.g., must not already be logged in) or post-conditions.

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, the description must disclose behavioral traits. It only states 'remove stored credentials', but doesn't mention side effects like session termination, reversibility, or authentication requirements.

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 sentence with no wasted words. It is concise, though slightly more detail could have been added without harming clarity.

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 0 parameters and no output schema, the description is too sparse. It fails to explain what 'removing credentials' entails, what the user should expect, or error conditions.

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 the schema coverage is 100%. The description doesn't need to add parameter info, and the baseline of 4 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 removes stored credentials, which is a specific action. However, it doesn't differentiate from sibling tools like 'login' or 'authenticate', which might also involve credential management.

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. The description is purely functional, without mentioning prerequisites or 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?

No annotations are present, and the description does not disclose behavioral traits such as whether the operation is read-only, rate limits, or permissions required.

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, no unnecessary words, front-loaded with the main 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?

The description is adequate for a simple search tool but omits details about the return format, which would be useful since no output schema exists.

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 schema already documents both parameters. The description adds no additional meaning beyond what the schema provides.

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 searches for trading pairs on a specific exchange, which distinguishes it from siblings like get_price or list_exchanges.

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 a direct reference to list_exchanges for finding exchange IDs, offering clear context for usage, though it doesn't explicitly state when not to use or 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?

The description discloses that this is a manual token-setting action, but no annotations exist. It does not cover side effects (e.g., overriding existing token), authentication needs, error behavior, or whether the token is validated. For a potentially sensitive operation, more transparency is needed.

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 short sentences with no extraneous words. Every part earns its place.

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

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

The description lacks any information about tool complexity, return values (no output schema), or success/failure behavior. For an advanced-use tool, more context is needed to ensure safe invocation.

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

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

Schema coverage is 100%, and the description does not add any value beyond the schema's parameter descriptions. According to rules, baseline is 3 when schema covers all parameters, and the description fails to add additional meaning.

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 ('set') and resource ('JWT token'), and the hint 'advanced use' differentiates it from simpler auth tools like authenticate or login. However, it does not explicitly distinguish from siblings that also deal with tokens.

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 only guidance is 'For advanced use only', which implies caution but does not specify when to use this tool versus alternatives like authenticate or login. No exclusions or prerequisites are provided.

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, the description must disclose behavioral traits. It only states the effect (bot stops) and that open positions remain. It fails to mention potential side effects, reversibility, permission requirements, or response behavior, which is insufficient for a mutation 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?

Two short sentences with no extraneous words; the main action is front-loaded. Every sentence contributes value.

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 that there is no output schema and the tool performs a mutation, the description should indicate the return value or confirmation behavior, and whether the bot must be running. It lacks these details, leaving the agent uncertain about the outcome.

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% and the schema description for 'id' is already clear. The tool description does not add any additional 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 action ('Stop') and the resource ('a running trading bot'), and adds a critical scope clarification ('Open positions remain'), which distinguishes it from related tools like deploy_bot or get_bot_status.

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, no prerequisites (e.g., bot must be running), and no conditions under which the tool should not be used.

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. It implies a read-only operation (suggesting strategies) but does not explicitly state non-destructiveness, authentication requirements, or any side effects. The description is adequate but lacks explicit behavioral disclaimers.

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 (two sentences) and front-loads the core action. Every word contributes to explaining the tool's purpose. However, it could be tightened slightly without losing meaning.

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

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

The description does not explain the output format (e.g., list of strategies with details), ordering, or any limitations. Given the absence of an output schema, the description should provide more context about what the agent can expect as a result.

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%, with all four parameters having individual descriptions. The main description merely summarizes these parameters without adding new meaning (e.g., data types, valid ranges, or interplay between filters). Baseline score of 3 applies as the description adds no value 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 uses the specific verb 'suggest' and specifies the resource 'trading strategies' while listing explicit filtering criteria (risk tolerance, max drawdown, preferred assets, Sharpe ratio). This clearly distinguishes the tool from siblings like 'list_strategies' or 'generate_strategy' by emphasizing personalization based on risk profile.

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 user wants strategies matching their risk profile, but it does not explicitly state when not to use the tool or provide alternatives (e.g., compare_strategies, explain_strategy). The differentiation from siblings is implicit rather than explicit.

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 present, so description carries full burden. It discloses async nature and timing, but lacks details on idempotency, concurrency limits, or side effects. Adds moderate value.

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 concise sentences covering purpose, async behavior, and return type. No unnecessary words, front-loaded with key 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 high-level purpose and async timing, but lacks parameter guidance, error scenarios, or output specifics. No output schema, and many sibling tools exist. Adequate but not comprehensive.

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 50% (some params described). Description adds no param details, failing to compensate for the uncovered parameters. Baseline of 3 not justified due to incomplete 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?

Description clearly states the action ('Run a backtest') and the resource ('on a strategy'). It differentiates from sibling tools like 'get_backtest_results' which retrieves existing results.

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 timing guidance ('Async, may take 30-120 seconds') but no explicit when-to-use or alternatives for already-run backtests. Limited differentiation from related tools.

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