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

With no annotations, the description carries the full burden. It does disclose destructive scope ('will cancel all pending orders'), which is genuinely useful. However, it omits permissions/auth requirements, behavior when no open orders exist, and whether results are per-order or a summary.

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, zero filler, with the operation and its scope stated first and the risk warning second. Nothing is extraneous.

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 one-parameter mutation with a fully documented schema and no output schema, the definition covers what the tool does and the main risk. Missing only the return shape and empty-state behavior, which keeps it short of a 5.

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 the single parameter is fully documented in the schema with examples (BTCUSDT, ETHUSDT). The description adds only the word 'specific symbol', which restates the schema; baseline 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?

States a specific verb (cancel), resource (all open orders), scope qualifier (for a specific symbol), and the venue (Binance USDⓈ-M Futures). The plural 'all orders' implicitly distinguishes it from the sibling cancel-order, which handles a single order.

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 a caution warning, not a when-to-use rule. It never tells the agent to prefer cancel-order for a single order, nor what precondition (existing open orders) makes this call 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, the description carries the full burden. It usefully discloses the constraint that only unexecuted/pending orders can be cancelled, but says nothing about error behavior (filled/cancelled orders), authorization requirements, or whether cancellation is irreversible.

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

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

Two tight sentences with the action front-loaded and no filler. The second sentence is mildly redundant but adds the pending-order qualifier rather than padding.

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 mutation tool with no annotations and no output schema, the description covers what and when but omits error semantics and confirmation of what a successful cancel destroys. Adequate but with clear gaps for a destructive 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?

Schema coverage is 100%, so the schema already documents symbol, orderId, and origClientOrderId. The description adds no information about parameter usage, such as whether orderId and origClientOrderId are alternatives or how they interact.

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

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

States a specific verb (cancel) and resource (order) with the venue scoped to Binance USDⓈ-M Futures. It implicitly separates itself from cancel-all-orders by saying 'an existing order', but doesn't name the sibling explicitly.

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

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

The second sentence gives a clear usage condition: cancel orders that are pending and not yet executed. It does not mention alternatives such as cancel-all-orders or modify-order, so no exclusions 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?

No annotations are provided, so the description carries the full burden. It says nothing about whether this affects only future positions or existing ones, whether changes fail on open positions, permission/auth requirements, or error behavior. "Initial leverage" is the only behavioral hint and is ambiguous.

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, front-loaded with the action. Efficient but the second sentence is somewhat promotional rather than informative.

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 mutation tool with no annotations and no output schema, the description omits critical context: effect on existing positions, failure conditions, and required permissions. Full behavioral burden is unmet.

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 both parameters including the 1-125 range and symbol examples. The description adds no additional parameter semantics beyond what the schema provides, which is 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?

States a specific verb ("Change") and resource ("initial leverage of a symbol") plus the product scope (Binance USDⓈ-M Futures). Clear enough to distinguish from siblings like change-margin-type or modify-position-margin, though it doesn't explicitly name them.

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

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

The phrase "Critical for risk management and position sizing" implies when you'd use it, but there is no explicit when-to-use vs alternatives guidance, nor any mention of prerequisites such as an open position or account state.

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 does not mention whether the change requires existing positions to be closed, whether it affects open orders, what permissions are needed, or whether the change is reversible. The only behavioral hint is a general property of isolated margin, not the tool's operational behavior.

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

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

Two sentences, front-loaded with the core action and platform, followed by a brief explanatory note. No wasted words; every sentence contributes to understanding.

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 mutation tool with no annotations and no output schema, the description is incomplete. It omits critical operational context such as whether positions must be flat, potential side effects on existing orders, authentication requirements, or error conditions. The added sentence about isolated margin is helpful but insufficient.

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 with examples and enum meanings. The description adds no parameter-level detail beyond what the schema provides, aligning with the baseline score of 3 when 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 states a specific verb (change) and resource (margin type), names the exact platform (Binance USDⓈ-M Futures) and the values (Cross and Isolated), which matches the enum in the schema. It distinguishes itself from sibling tools like change-leverage or modify-position-margin by focusing squarely on margin type.

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 the action's context but does not explicitly say when to use this tool versus alternatives such as modify-position-margin or change-leverage. The added note about isolated margin limiting risk provides some strategic rationale but no exclusions or alternative routing.

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 the well-known constraint that Binance rejects this change while open positions or orders exist, nor whether the swap is account-wide, reversible, or permission-gated. For a mutation of account-level trading behavior this is a significant gap.

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

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

Two tight sentences, front-loaded with the action and domain, with zero filler. The definitional clause about Hedge Mode is mildly redundant but does aid comprehension of the mode names.

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 mutation tool with no annotations and no output schema, the description omits the preconditions that determine whether the call succeeds (no open positions/orders), the scope of the change, and the required account/permission context. It is underspecified for the risk profile of the 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?

Schema description coverage is 100% and the single enum-typed parameter is fully documented ('true for Hedge Mode, false for One-way Mode') in the schema itself. The description adds no syntax or default detail beyond that, so the baseline 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?

States a specific verb (change) and resource (position mode) with the exact domain (Binance USDⓈ-M Futures) and names both modes involved. It cannot be confused with any sibling like change-leverage or change-margin-type.

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 second sentence explains what Hedge Mode means but gives no when-to-use guidance, no prerequisites, and no indication of how this relates to siblings such as new-order. The agent must infer the calling context entirely.

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, so the description carries the full burden. It mentions the domain (Binance USDⓈ-M Futures) and what is returned, but omits behavioral traits like authentication requirements, rate limits, or whether it's a read-only call. With zero annotations, a 3 is appropriate for partial disclosure of 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?

Two sentences, front-loaded with the core purpose and then the value proposition. No wasted words, though it could be slightly more structured with explicit when-to-use guidance.

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 no-param, no-annotation tool, the description covers what it returns and why it's useful. However, given the complexity of a futures trading API, it lacks critical operational details like authentication needs, rate limits, or error behavior that an agent might need to invoke 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 tool has zero parameters, so the baseline is 4. The description adds no parameter information, which is correct since there are none.

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

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

States a specific verb (Get) and resource (current account information) plus the exact scope (balances, margin, positions) for Binance USDⓈ-M Futures. Clearly distinguishes from siblings like get-position, which returns only 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?

Implies usage for risk management and portfolio tracking, which gives context for when to call it. However, it doesn't explicitly state when to use it versus get-position or get-open-orders, or any 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?

No annotations are provided, so the description must carry the behavioral burden. It discloses the returned status set and that this is a read-style history listing, but says nothing about pagination behavior, rate limits/weight, or whether time-window restrictions apply to this endpoint.

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, front-loaded with the core action and scope, with the use case in the second sentence. No filler or 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 read-only listing tool with a fully documented schema but no annotations or output schema, the description covers scope and intent adequately. It could be more complete by noting pagination/return behavior, since no output schema exists to fill that 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?

Schema description coverage is 100%, so all five parameters are already documented in the schema (limit defaults/max, orderId semantics, time ranges). The description adds no parameter-level meaning beyond that, which is the baseline expectation.

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

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

States a specific verb ('Get'), resource ('all orders'), and the enum of statuses returned (open, filled, cancelled) scoped to Binance USDⓈ-M Futures. The enumeration of statuses implicitly separates it from get-open-orders, though no sibling is named 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?

'Useful for order history and auditing' gives an implied use case but no explicit when-to-use-vs-alternative guidance, e.g. when to pick this over query-order or get-open-orders. Sibling differentiation is left to inference.

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 does not mention authentication requirements, rate limits, pagination, or whether the call is read-only (though 'Get' implies it). For a market-data query against a live venue like Binance, those traits matter.

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 waste; the core purpose is front-loaded. The second sentence is somewhat generic filler but does hint at intended use.

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 purpose and a light use case, which fits a simple one-parameter read tool. However, with no annotations and no output schema, it leaves unstated whether the call is read-only, authenticated, or paginated, which an agent would benefit from knowing.

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 single optional symbol parameter is fully documented in the schema. The description adds no parameter detail beyond what the schema provides, making the baseline 3 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?

States a specific verb (Get) and resource (all current open orders) scoped to Binance USDⓈ-M Futures. It is clearly distinguished from siblings like get-all-orders, query-order, and get-trade-history by the 'open' qualifier.

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?

Gives contextual usage ('monitoring pending orders and managing active trades') but does not explicitly state when to prefer this over query-order, get-all-orders, or when it should not be used. Usage is implied 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?

With no annotations, the description carries the full burden. It does disclose the payload shape (entry price, size, PnL, margin used) and implies a read-only operation via 'Get'/'Returns', which is useful given there is no output schema. However, it says nothing about authentication requirements, whether it is a signed/private endpoint, rate limits, or whether PnL is realized/unrealized, leaving meaningful 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?

Two sentences, no filler: the purpose and platform come first, the return contents second. Every clause earns its place.

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

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

For a one-parameter read tool with no annotations and no output schema, the description is nearly sufficient: it identifies the platform and summarizes the returned fields. Only the missing auth/rate-limit context and the distinction between position-scoped versus account-wide responses keep it from being 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% and the single parameter's description already explains the symbol format and the no-symbol default. The description adds no syntax, case, or filtering detail beyond the schema, so the baseline 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 names a specific verb ('Get'), resource ('position information'), and scope ('Binance USDⓈ-M Futures'), and enumerates what the response contains. It does not explicitly contrast itself with nearby siblings such as get-open-orders or get-account, but the resource is unambiguous since no other sibling reads 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?

There is no statement of when to use this tool versus alternatives, nor any prerequisites or exclusions. The 'if symbol omitted returns all positions' behavior is only conveyed in the schema, not the description.

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 carry the behavioral load. It discloses that only filled/executed trades are returned (vs open orders) and lists what data fields (price, quantity, fees) are included, which is useful. But it says nothing about authentication requirements, rate limiting, pagination behavior, or time-range defaults beyond what the schema already implies.

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, efficient and front-loaded with the core purpose. No filler. Slightly could be tightened but 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?

For a read-only query tool with full schema coverage but no annotations and no output schema, the description covers the core (what it returns) but omits auth requirements, pagination limits, and how it differs operationally from sibling order-query tools. Adequate but with clear 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?

Schema description coverage is 100%, so the schema fully documents all 5 parameters (limit defaults/max, fromId, symbol format, start/end time). The description adds the framing that results are filled trades filtered presumably by the time/ID params, but no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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

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

States a specific verb (Get) and resource (account trade list) and names the domain (Binance USDⓈ-M Futures). It distinguishes itself from get-all-orders and query-order by specifying executed/filled trades, though it does not explicitly name those siblings.

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 versus query-order, get-all-orders, or get-open-orders. The parenthetical '(executed trades)' hints at filled-only scope but does not explicitly state the condition or exclusions, and no prerequisites (auth, symbol validity, rate limits) 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 provided, so the description carries the full burden. It adds one real behavioral fact — that it targets pending (not filled) orders — but omits permissions/auth requirements, error behavior, and which order types are modifiable. Minimum viable, not rich.

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

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

Two tightly constructed sentences with no filler; the core action is front-loaded and the second sentence adds the differentiating benefit.

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 mutation tool with zero annotations and no output schema, the description is adequate on scope but thin on behavior: no auth/precondition info, no indication of what happens on rejection, and no guidance on mutually exclusive identifiers. Enough to call it, not enough to call it confidently.

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 all six parameters are already documented. The description only echoes price and quantity, adding no format, constraint, or precedence meaning beyond the schema (e.g., how orderId and origClientOrderId interact). Baseline 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?

States a specific verb (Modify) and resource (an existing order) and pins the venue (Binance USDⓈ-M Futures). The phrase 'without canceling and recreating them' implicitly separates it from cancel-order and new-order, so an agent can route to it without opening either schema.

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?

Gives clear context: use it for updating price or quantity of pending orders. It also implies the alternative workflow (cancel + new order) it replaces. No explicit when-not or named alternatives, which keeps it out of the top band.

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 behavioral burden. It usefully discloses the isolated-margin-only scope and the intended effect (adjusting risk, preventing liquidation), but says nothing about permissions, reversibility, rate limits, or error behavior for what is a financial mutation.

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

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

Two tight sentences, front-loaded with the operation and scope, with zero redundant or filler 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?

Parameters are fully covered by the schema, but this is a mutation on a live futures position with no annotations and no output schema, so the definition should do more to convey prerequisites and result behavior than it does.

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 type (1=add, 2=reduce), amount, and symbol semantics are already fully documented in the schema. The description's 'add or reduce' phrasing mirrors the schema without adding format or constraint detail, so the baseline 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?

States a specific verb+resource ('Modify isolated position margin') scoped to Binance USDⓈ-M Futures, which is clearly distinguishable from siblings like change-leverage and change-margin-type. It doesn't explicitly name a sibling, but the resource is specific enough that no schema opening is required to tell it apart.

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?

Gives a clear use context: add or reduce margin to adjust position risk and prevent liquidation. However, it names no alternatives (e.g., change-leverage, change-margin-type) and states no when-not conditions, so routing is left partly to inference.

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 mentions supported order types, but does not disclose authentication requirements, error handling, idempotency, or what happens on partial fills. It only lists order types, which is already in the schema enum. This is a significant gap for a mutating financial 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?

Three sentences, front-loaded with the core action and venue. The list of order types is long but relevant. No wasted words, though the middle sentence is somewhat redundant with the 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 complex trading operation with 16 parameters, no annotations, and no output schema, the description is insufficient. It does not explain return values, error cases, or prerequisites like API permissions or account funding. An agent would need to infer critical details.

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 provides detailed semantics for all 16 parameters (enums, required fields, dependencies). The description adds no parameter-level guidance; it merely lists order types already covered by the enum. Baseline 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?

States a specific verb (Create) and resource (order) on a specific venue (Binance USDⓈ-M Futures). The name 'new-order' and siblings like cancel-order, query-order make its role unambiguous.

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?

Says it is 'essential for executing trades on futures markets,' implying when to use it, but does not name alternatives or note when not to use it (e.g., use modify-order to change an existing order). The guidance is implied 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 are present, so the description carries the full disclosure burden. It implies a read-only lookup via the filled/pending/cancelled outcome, but says nothing about authentication/API-key requirements, rate limits, the fact that Binance order queries typically only cover recent orders, or the error behavior when an order is not found.

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, zero filler, purpose front-loaded before the outcome hint. Efficient, though the second sentence is the only guidance offered and nothing structurally elaborates on identity or failure cases.

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 annotations and no output schema, the description must compensate more than it does. It omits authentication prerequisites and does not resolve how an order is identified given that only symbol is required in the schema, leaving a real risk of a malformed call.

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 symbol, orderId, and origClientOrderId; baseline is 3. The description adds no additional parameter meaning — notably it does not clarify the key ambiguity that the schema marks only symbol as required while one of orderId or origClientOrderId is presumably needed to identify the order.

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

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

States a specific verb (Query) and resource (status of a specific order) plus the venue (Binance USDⓈ-M Futures), so the agent knows exactly what it does. It does not, however, distinguish itself from close siblings such as get-open-orders or get-all-orders, which also return order 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?

"Use this to check if an order was filled, pending, or cancelled" gives an implied use case but names no alternatives and no exclusions. It never says to prefer get-open-orders for bulk listing or what to do when the target order is older than the query window.

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