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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly discloses that the function does not execute transactions, returns an unsigned transaction, and uses the configured wallet as maker. This goes beyond the name and schema, making the behavior transparent. It could be slightly more detailed about potential error scenarios, but the core traits are covered.

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 structured with a main sentence, an explanation, an Args section, a Returns section, and a Note, followed by a complete example. It is front-loaded with the core purpose. The example is useful but somewhat lengthy, yet every part adds context. It is appropriately sized for the tool's complexity.

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 fully explains the return format (success, data with transaction and requestId, error) and the necessary follow-up action (executing the unsigned transaction). It also covers the 'uses configured wallet as maker' aspect. Given the modest complexity and the availability of an output schema (as indicated by context), the description is nearly complete. It might include edge-case handling or alternative tools, but those are 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?

The schema provides no description for the 'order' parameter (0% coverage), so the description must compensate. It does: 'Args: order: Order account address to cancel' clearly explains what the parameter is and what it identifies. The example reinforces this with 'your_order_account_address_here'. This is sufficient for a single-parameter tool.

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 'Cancel a single active limit order' with a specific verb and resource. It explicitly differentiates from the sibling 'cancel_limit_orders' by saying 'single', and from 'execute_limit_order' by noting it only returns an unsigned transaction versus executing it.

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

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

The description provides clear context for use: it says the call is free, does not execute transactions, and returns an unsigned transaction that must be signed and executed. It gives an example showing the follow-up use of 'execute_limit_order'. However, it does not explicitly mention when to prefer this over 'cancel_limit_orders' or other alternatives, so it misses the explicit exclusion criterion.

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 fully discloses behavioral traits: it is free, performs no transactions, returns unsigned transactions, and requires each to be signed and executed separately. It also documents the 'success' and 'requestId' response fields, covering safety and workflow expectations.

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 well-structured with intro, Args, Returns, Note, and Example sections. It is concise for the tool's complexity, with the main purpose stated upfront and no redundant information.

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

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

Given the tool's complexity (batching, unsigned transactions, optional input, separate execution), the description covers all necessary aspects, including multi-transaction behavior and example usage. The presence of an output schema does not reduce the completeness since the description still explains critical workflow 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?

The schema only defines 'orders' as an array/null with no description. The description adds essential meaning: 'Array of order account addresses' and the special case that None/empty cancels ALL orders. Since schema description coverage is 0%, this fully compensates.

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 'Cancel multiple limit orders (batched in groups of 5)' with a clear verb and resource. It also clarifies the empty-input behavior (cancels ALL orders), which distinguishes it from the sibling tool 'cancel_limit_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?

It provides clear when-to-use context, including 'FREE to call', 'does not execute any transactions', and that it returns unsigned transactions requiring separate signing/execution. However, it does not explicitly reference alternative tools or state 'when not to use', though the batching vs. singular nature is implied.

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

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

With no annotations provided, the description carries full burden and delivers: it states the function is free, does not execute transactions, returns an unsigned transaction, discloses price validation gaps, min order size, transfer tax, slippage behavior, and referral inclusion.

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?

Though lengthy, the structure uses headings, numbered warnings, and an example. The content is dense with essential warnings rather than filler; every section 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?

The description covers purpose, parameters, return structure, warnings, and includes a realistic example with both safe and dangerous cases. Given the tool's complexity and dangerous failure modes, it is 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 descriptions are absent (0% coverage), but the 'Args' section explains each parameter including units (smallest unit, basis points, Unix timestamp) and provides concrete examples showing decimals.

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 opens with a clear, specific statement: 'Create a limit order that executes when target price is reached.' It further clarifies it returns an unsigned transaction, distinguishing it from execution/cancellation 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?

It provides extensive context on when to use this tool (to create a limit order without executing) and warns against misuse (price validation, transfer tax, minimum size). However, it does not explicitly name alternative tools like execute_limit_order or get_swap_quote, so it lacks explicit 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?

With no annotations, the description fully discloses the paid nature, on-chain execution, automatic order matching, fees, minimum order size, and return structure. It also warns about creating a real order, giving the agent a clear safety profile.

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 well-structured with a warning, summary, args, returns, notes, and example. It is longer than minimal but every section adds value; the example is practical. The attention-grabbing warning is slightly theatrical but not wasteful.

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, inputs, outputs, fees, execution behavior, and workflow, making it complete for a two-parameter tool. The presence of an output schema is supplemented by the detailed return description, so nothing essential is missing.

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 description explicitly explains both parameters: transaction is 'Base64 encoded unsigned transaction from create_limit_order' and request_id is 'Request ID from create_limit_order response'. This adds meaning far beyond the schema's bare string definitions.

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 'Sign and execute a limit order transaction' and specifies it creates a limit order on Solana. It distinguishes from siblings like execute_swap_transaction by emphasizing limit order and by referencing create_limit_order as the source of inputs.

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

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

The description provides clear context: it is a paid operation used after create_limit_order, with an example illustrating the create-then-execute workflow. It does not explicitly mention alternatives or when not to use, but the context is sufficient for an agent to select it appropriately.

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 and excels: it warns about irreversible spending, mentions signing with a configured private key, and outlines the execution steps. It also discloses the non-reversible nature and actual cost, going well beyond basic read/write hints.

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?

Although long, the description is efficiently structured with a clear warning, numbered steps, args, returns, and an example. Every section adds critical information and none is redundant or filler, making it appropriate for a high-stakes operation.

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, irreversible transaction tool, the description covers the execution pipeline, prerequisites (quote retrieval), parameter meanings, return format, and an example. It is fully self-contained even without an output schema shown, addressing all necessary context.

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 only type and title, but the description explains 'transaction' is a base64 encoded UNSIGNED transaction from get_swap_quote and 'request_id' is from the swap quote response. This contextualizes both parameters and even includes an example showing exactly how to pass them, compensating fully for zero 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 it 'Sign and execute a swap transaction via Jupiter Ultra API' and emphasizes it executes a REAL trade spending actual SOL. This distinguishes it from sibling tools like execute_limit_order while specifying the exact resource (swap transaction) and action (execute).

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?

It explicitly says 'Only call this function when you want to actually execute a trade' and provides a clear pre-requisite flow via get_swap_quote. The example shows the sequence of obtaining a quote then executing, making when-to-use unmistakable.

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 discloses key behaviors: the call is free, does not execute transactions, uses a configured wallet if none is provided, and returns a structured dictionary with success/error handling. This goes beyond what the schema indicates.

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 well-structured with Args, Returns, and an Example. It is appropriately sized – every section contributes to understanding, including code snippets illustrating both usage patterns.

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 fully covers the tool's behavior, parameter, return format, and example usage. Given the tool's simplicity and the presence of a detailed return outline, no critical information is missing.

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 only provides the parameter name and default, with no description. The description explains the parameter's meaning and optional fallback, adding semantics 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 'Get token balances for a wallet address via Jupiter Ultra API.' It distinguishes itself from sibling tools like execute_swap_transaction by explicitly noting it does not execute transactions, making its purpose 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?

The description provides a clear usage context: 'Use this to check wallet holdings before making trades.' It does not explicitly state when not to use it or list alternative tools, but the context is sufficient for an AI agent to select it for read-only balance checks.

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 discloses the critical non-mutating behavior ('does not execute any transactions') and free cost. It also explains return fields including error handling. It does not cover rate limits or auth prerequisites in depth, but the 'configured wallet' implication touches on context.

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

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

The description is well-structured with a clear purpose statement, Args bullet list, Returns list, and a helpful example. It is slightly verbose (the example could be trimmed), but every section serves a purpose and the information is 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 5 parameters, no annotations, and no explicit output schema, the description provides complete coverage: purpose, parameter details, return value structure, pagination behavior, and a usage example. It leaves little ambiguity for an agent to invoke the tool 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 schema has 0% description coverage, but the Args section explains each of the 5 parameters with defaults, semantics, and optionality (e.g., order_status default active, wallet defaults to configured wallet). This fully compensates for the bare schema and adds meaning well beyond field titles.

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 opens with 'Get active or historical limit orders for a wallet', using a specific verb ('Get') and resource ('limit orders') with clear scope. It distinguishes itself from sibling tools like create_limit_order and cancel_limit_order by explicitly framing this as a read-only query operation.

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 statement 'This function is FREE to call and does not execute any transactions' provides clear context that it is safe to use for checking orders. However, it does not explicitly contrast with alternatives or state when not to use it (e.g., when needing to create or cancel an order), so it stops short of a 5.

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?

Despite having no annotations, the description fully discloses behavior: it is free, performs no transactions, and returns a dictionary with success/warnings/error keys. It details the specific warning types and their severity levels, warning about risks like mint and freeze authorities. This goes well beyond a 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 lengthy but well-organized into purpose, parameter explanation, return format, warning types, and example. Every section adds value; the length is justified given the tool's complexity. However, it could be slightly tightened by condensing the warning descriptions without losing critical detail.

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

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

The description is self-contained for an agent: it explains how to call the tool, what the response looks like, how to interpret warnings, and provides a complete usage example. The output schema exists, but the description's return format details and warning semantics are more informative, making it 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 schema provides only a string parameter named 'mints' with no description, and schema coverage is 0%. The description compensates exceptionally: explains comma-separated format, provides an explicit example, notes no spaces, and mentions no specific limit. This is essential guidance for correct invocation.

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 opens with a specific action ('Get token security information') and clearly identifies the resource (Jupiter Ultra Shield API). It adds important context that the call is free and transactional, distinguishing it from trade-related siblings like get_swap_quote and execute_swap_transaction.

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 states when to use it: 'Use this to check token security before making trades' and 'Essential for avoiding scam tokens.' It also provides an efficiency guideline (comma-separated mints in one request) and notes it does not execute transactions, which implies safe usage. Though no alternatives are named, the tool's unique purpose is clear.

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. It discloses that the call is free, does not execute transactions, and returns an unsigned transaction with a requestId for later execution. It could add more detail about the transaction format or API key requirements, but the essential behavior is transparent.

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 well-structured with an overview, Args, Returns, and a concrete example. Every section adds value, and the length is appropriate for the tool's complexity.

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, parameters, return structure, and a usage example. Given the tool's simple nature and the absence of annotations, this description is sufficiently complete for an agent to select and invoke the tool correctly.

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

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

The input schema has zero description coverage, but the description fully compensates. Each parameter is explained with examples, including the meaning of 'amount' in smallest units and concrete mint addresses for SOL and USDC. This significantly exceeds the schema's bare property names.

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 action: 'Get a swap quote and unsigned transaction from Jupiter Ultra API.' It clearly identifies the resource and outcome, and explicitly distinguishes from execution tools by noting it 'does not execute any transactions.'

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?

It provides clear usage context: 'Use this to get price quotes and prepare transactions for execution.' It also gives an implicit exclusion ('does not execute any transactions') that separates it from execution-oriented siblings, though it does not name specific alternative tools.

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

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

With no annotations provided, the description carries full responsibility. It discloses that the function is free, does not execute transactions, includes response limits (20 tokens per symbol/name search, up to 100 mint addresses), and describes the return dictionary structure (success, query, data, error). These are key behavioral traits beyond what annotations would provide.

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

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

The description is relatively long but well-structured with headings, an Args section, Returns section, and multiple examples. Some examples are redundant, and trimming could shorten it, but it remains clear and front-loaded with the key purpose and safety note.

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

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

Given one parameter, no annotations, and existing output schema not shown, the description is complete. It covers purpose, usage, parameter semantics, return format, and limitations, and provides examples. No critical information is missing.

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 has one parameter 'query' with no description (0% coverage). The description fully compensates by explaining valid input types: symbol, name, mint address, comma-separated multi-queries, and limits. This is exemplary parameter documentation.

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 tokens via the Jupiter Ultra API, specifically to find mint addresses when only symbol or name is known. This specific verb+resource+scope distinguishes it from sibling tools that handle swaps, orders, and balances.

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?

It explicitly states when to use this tool ('Use this to find token mint addresses when you only know the symbol or name') and emphasizes that it is free and does not execute transactions, making it safe for lookups. It also recommends multi-token searches for efficiency, providing clear usage context.

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