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

With no annotations provided, the description carries the full burden. It discloses that the tool creates/returns a 'debt_id', indicating a write operation, but lacks details on permissions, error handling, or side effects. It adds some behavioral context (e.g., APR format), but doesn't cover critical aspects like whether this is idempotent or has rate limits.

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 front-loaded with the core purpose, followed by usage guidelines and a key parameter note. Every sentence adds value without redundancy, and the structure efficiently conveys essential information in three concise lines.

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 write tool with 7 parameters, 0% schema coverage, and no output schema, the description is incomplete. It covers purpose, usage, and one parameter well, but misses details on other parameters, return values beyond 'debt_id', and behavioral traits like error conditions. Given the complexity, more context is needed for full adequacy.

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 0%, so the description must compensate. It clarifies the 'apr' parameter semantics ('percentage, e.g., 18.5 for 18.5%'), which is crucial beyond the schema's type. However, it doesn't explain other parameters like 'balance' units or 'next_payment_due_date' format, leaving gaps for the remaining 6 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 specific action ('Track a debt') and resource ('that isn't behind a linked Plaid account'), distinguishing it from sibling tools like 'list_external_debts_tool' and 'update_external_debt_tool'. It provides concrete examples of use cases (BNPL, medical bills, 401(k) loans), making the purpose highly specific and differentiated.

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 explicitly states when to use this tool ('Use for BNPL, medical bills, 401(k) loans, or debts at non-linkable lenders'), providing clear context for its application. It distinguishes this from tools that handle linked accounts (implied by the sibling list), though it doesn't name specific alternatives, the guidance is comprehensive for the given 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool removes an APR override, implying a destructive mutation, but doesn't clarify permissions needed, whether the action is reversible, or what happens on success/failure (e.g., confirmation message or error). This leaves significant gaps 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?

The description is a single, efficient sentence with zero wasted words, directly stating the tool's function. It is appropriately sized and front-loaded, making it easy for an agent to parse quickly without unnecessary detail.

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

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

Given the tool's complexity as a mutation operation with no annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't cover behavioral aspects like error handling or return values, nor does it fully explain parameter usage, leaving the agent under-informed for safe and effective 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?

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It implies 'account_id' is used to identify the target account, which adds basic meaning, but doesn't specify format (e.g., numeric ID, string) or validation rules. This provides marginal value, aligning with the baseline for partial compensation.

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 ('Remove') and target ('APR override for an account'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'set_account_override_tool' or 'list_overrides_tool', which would require mentioning those alternatives to achieve a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'set_account_override_tool' (for adding/updating overrides) or 'list_overrides_tool' (for viewing them). It also lacks prerequisites, such as whether an override must exist to be removed, leaving the agent with insufficient context for optimal selection.

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

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

With no annotations provided, the description carries full burden but lacks critical behavioral details. It mentions exchanging tokens and caching accounts but doesn't disclose authentication requirements, rate limits, error conditions, or what 'caches accounts' entails operationally. The description provides basic intent but insufficient behavioral 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 perfectly concise with two focused sentences that front-load the main purpose. Every word earns its place—no redundancy or unnecessary elaboration while clearly communicating the tool's role in a workflow.

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

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

Given no annotations, 0% schema coverage, no output schema, and 2 parameters, the description provides adequate basic context but lacks completeness. It explains the tool's role in a Link session workflow but misses details about authentication, error handling, return values, and parameter specifics needed for reliable 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?

With 0% schema description coverage for 2 parameters, the description adds minimal semantic value. It mentions 'link_token' indirectly via 'public_token' but doesn't explain parameter purposes, relationships, or the 'timeout_seconds' default behavior. The description partially compensates but leaves significant gaps in parameter understanding.

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 with specific verbs ('Finalize', 'Exchanges', 'caches') and resources ('Link session', 'public_token', 'access_token', 'accounts'). It distinguishes itself from siblings like 'link_account' by focusing on completion rather than initiation.

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

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

The description provides clear context for when to use this tool ('once the user has completed [a Link session] in their browser'), implying it should follow an initial linking process. However, it doesn't explicitly state when not to use it or name specific alternatives among siblings.

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 discloses key behavioral traits: 'Live balance lookup' implies read-only operation, 'hits Plaid' indicates external API calls, and 'not cached' clarifies data freshness. However, it doesn't cover error handling, rate limits, authentication needs, 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 extremely concise and front-loaded: two brief sentences with zero wasted words. Every phrase ('Live balance lookup', 'hits Plaid, not cached', 'Filter by account_id if given') adds distinct value without 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?

Given the tool's moderate complexity (single optional parameter, external API calls), no annotations, and an output schema (which handles return values), the description is minimally adequate. It covers the core purpose and parameter use but lacks details on error cases, performance implications, or integration with 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?

The description adds meaningful context for the single parameter: 'Filter by account_id if given' clarifies its optional filtering purpose. With 0% schema description coverage and no parameter documentation in the schema, this compensates well. However, it doesn't specify the account_id format or constraints.

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: 'Live balance lookup' specifies the verb and resource, and '(hits Plaid, not cached)' adds technical context. However, it doesn't explicitly differentiate from sibling tools like 'list_accounts_tool' or 'get_holdings_tool' beyond the balance focus.

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

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

The description provides some usage context: 'Filter by account_id if given' implies optional filtering, and 'hits Plaid, not cached' suggests real-time data needs. However, it lacks explicit guidance on when to use this versus alternatives like 'list_accounts_tool' or 'get_holdings_tool', and doesn't mention prerequisites 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It implies a read-only operation by describing data retrieval, but doesn't specify whether authentication is required, rate limits exist, what happens when account_id is null, or the format/structure of returned data. The description is minimal and lacks important behavioral context for a financial data tool.

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

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

The description is extremely concise - a single sentence that efficiently communicates the core purpose and data fields. Every word earns its place, with no wasted text or redundancy. The structure is front-loaded with the main purpose followed by specific data elements in parentheses.

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 financial data retrieval tool with no annotations, no output schema, and incomplete parameter documentation, the description is inadequate. It doesn't explain what happens when account_id is null (all accounts vs default account), doesn't describe the return format, and provides no context about authentication, permissions, or data freshness. The description is too minimal given the complexity of financial data 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?

The description provides no information about the account_id parameter, which has 0% schema description coverage. However, with only one parameter that's optional (defaults to null), the baseline is higher. The description doesn't compensate for the lack of parameter documentation, but the simplicity of a single optional parameter keeps this from being a critical failure.

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 'current investment positions' and lists the specific data fields returned (tickers, quantities, market value, cost basis). It uses a specific verb ('positions') and identifies the resource (investment holdings), though it doesn't explicitly distinguish from sibling tools like get_balances_tool or get_investment_transactions_tool.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like get_balances_tool (which might provide different financial data) or get_investment_transactions_tool (which might show transaction history rather than current positions), nor does it specify any prerequisites or context for usage.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what data is retrieved but does not cover critical aspects like whether this is a read-only operation, authentication requirements, rate limits, or error handling. For a data retrieval tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy to understand quickly, though it could be slightly more structured with additional details.

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 (data retrieval with one parameter), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It does not explain return values, error cases, or how the parameter affects the query, leaving significant gaps for an AI agent to understand full usage.

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

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

The input schema has one parameter (account_id) with 0% description coverage, and the tool description does not mention parameters at all. Since schema coverage is low, the description fails to compensate by explaining the parameter's role or semantics. With no parameter information in the description, it adds no value beyond the schema, resulting in a baseline score.

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 specific identity data (names, emails, phones, addresses) from an institution, which is a specific verb+resource combination. However, it does not explicitly differentiate from sibling tools like 'list_accounts_tool' or 'get_balances_tool', which might also involve account data but for different purposes, leaving some ambiguity in sibling differentiation.

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 whether it's for a specific account or all accounts, or how it relates to siblings like 'list_accounts_tool'. It implies usage for identity data but lacks explicit context, exclusions, or prerequisites, resulting in minimal actionable 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 of behavioral disclosure. It mentions a prerequisite (Income product enabled) but doesn't describe other key traits such as whether this is a read-only operation, potential rate limits, authentication needs, or what the return format looks like. For a tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is extremely concise with two sentences that directly state the purpose and a key prerequisite. Every word earns its place, and it's front-loaded with the core functionality. There's no wasted text 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?

Given the tool has no parameters (simplifying input) and no output schema (increasing the need for output description), the description is moderately complete. It covers the purpose and a prerequisite but lacks details on behavioral traits (e.g., read-only status, return format) and doesn't explain what the output contains, which is a gap since there's no output schema to rely on.

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 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. A baseline of 4 is applied since no parameters exist, and the description doesn't mislead about inputs.

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

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

The description clearly states what the tool does ('Bank-detected income streams') with a specific resource (income streams) and verb (detected). It distinguishes from siblings like get_balances_tool or get_transactions_tool by focusing on income data rather than balances or transactions. However, it doesn't specify the exact scope (e.g., all income streams vs. recent ones), keeping it from a perfect 5.

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

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

The description provides some usage context by stating 'Requires Income product enabled in your Plaid dashboard,' which implies a prerequisite condition. However, it doesn't explicitly guide when to use this tool versus alternatives (e.g., vs. get_holdings_tool for investment income) or mention any exclusions, leaving the guidance incomplete.

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 implies a read operation by listing transaction types, but lacks details on permissions, rate limits, pagination (despite a 'limit' parameter), or response format. For a tool with 4 parameters and no annotations, this is insufficient behavioral 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 extremely concise—a single phrase with zero waste. It's front-loaded with the core purpose, though this brevity comes at the cost of detail. Every word earns its place by specifying the transaction types.

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 4 parameters with 0% schema coverage, no annotations, and no output schema, the description is incomplete. It doesn't address parameter usage, behavioral traits, or output expectations, making it inadequate for a tool of this complexity. The agent lacks critical context to use it effectively.

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

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

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It mentions 'Brokerage transactions' but doesn't explain how parameters like 'start_date', 'end_date', 'account_id', or 'limit' affect the query. The description adds minimal value beyond the schema's parameter 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 clearly states the tool retrieves brokerage transactions (buys, sells, dividends, fees), providing a specific verb ('Brokerage transactions') and resource scope. However, it doesn't explicitly differentiate from sibling tools like 'get_transactions_tool' or 'search_transactions_tool', which likely handle similar data but with different filtering or scope.

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 offers no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for usage, or compare to sibling tools like 'get_transactions_tool' or 'search_transactions_tool', leaving the agent to infer based on tool names alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read operation by listing data fields, but doesn't specify if it requires authentication, returns all liabilities or filtered ones, handles errors, or has rate limits. This leaves significant gaps for a tool with potential data sensitivity.

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

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

The description is a single, efficient sentence that lists key elements without fluff. It could be slightly more structured by front-loading the action (e.g., 'Retrieve liabilities such as...'), but it's appropriately sized and clear.

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

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

Given no annotations, no output schema, and the tool's complexity (retrieving financial data), the description is incomplete. It lists data fields but doesn't explain return format, error handling, or scope (e.g., all accounts or filtered), making it inadequate for safe and effective use by an AI agent.

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

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

The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description doesn't add param info, which is appropriate here. Baseline is 4 for zero parameters, as it avoids unnecessary detail.

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 lists types of liabilities (credit cards, student loans, mortgages) and data fields (APRs, balances, due dates), which implies a retrieval function. However, it lacks an explicit verb like 'retrieve' or 'list', making the purpose somewhat vague rather than clearly stated as a specific action. It distinguishes from some siblings like 'add_external_debt_tool' by implying read-only access, but not all.

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 is provided. The description hints at retrieving liability data, but it doesn't specify contexts, prerequisites, or compare to siblings like 'get_balances_tool' or 'summarize_debt_tool', leaving usage unclear without external 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?

With no annotations provided, the description carries full burden. It discloses key behavioral traits: the data is cached (implying potential staleness), requires prior sync for freshness, and clarifies amount semantics ('Positive amounts = spend'). However, it doesn't mention pagination behavior, rate limits, error conditions, 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?

Three concise sentences with zero waste. First establishes purpose, second provides date format and prerequisite, third clarifies amount semantics. Each sentence earns its place by adding distinct, valuable 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 8 parameters with 0% schema coverage, no annotations, but an output schema exists, the description provides adequate context. It covers the core purpose, prerequisite, date format, and amount interpretation. The output schema handles return values, so the description focuses on usage context appropriately.

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 0%, so the description must compensate. It adds crucial semantic context: date format ('YYYY-MM-DD'), amount interpretation ('Positive amounts = spend'), and implies filtering capabilities. While it doesn't detail all 8 parameters individually, it provides enough guidance for effective use given the output schema exists.

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: 'Query cached transactions' specifies both the verb (query) and resource (cached transactions). It distinguishes from siblings like 'search_transactions_tool' by emphasizing the 'cached' aspect, though it doesn't explicitly contrast with all similar tools.

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

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

The description provides clear usage guidance: 'Run sync_transactions first to refresh' indicates a prerequisite. It distinguishes from 'sync_transactions_tool' by positioning this as a query tool for cached data, though it doesn't explicitly state when NOT to use it or compare with 'search_transactions_tool'.

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 discloses key behavioral traits: it initiates a session, returns a URL for user authentication, and requires a follow-up call to 'complete_linking'. However, it lacks details on error handling, timeouts, or authentication requirements, which are relevant for a session initiation tool.

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

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

The description is front-loaded with the core purpose in the first sentence, followed by essential usage details. Every sentence earns its place with no wasted words, making it highly efficient and easy to parse.

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 (session initiation with a follow-up step), no annotations, and no output schema, the description is mostly complete. It covers the purpose, usage flow, and output, but could improve by mentioning potential errors or the URL's validity duration for full contextual coverage.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description adds value by explaining the output (a URL) and the subsequent action, which compensates for the lack of output schema, though it doesn't detail the URL format.

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 specific action ('Start a new Plaid Link session') and resource ('Plaid Link'), distinguishing it from siblings like 'complete_linking' or 'list_linked_institutions_tool'. It uses precise verbs and identifies the exact functionality.

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 explicitly states when to use this tool ('Start a new Plaid Link session') and provides a clear alternative ('call complete_linking with the returned link_token'), guiding the agent on the workflow sequence without ambiguity.

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 discloses that the tool lists accounts from a local cache, which is useful behavioral context about data freshness. However, it lacks details on permissions, rate limits, or error handling, leaving gaps for a tool with no annotation support.

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

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

The description is a single, efficient sentence that front-loads the key action and scope without any wasted words. It directly communicates the tool's purpose and data source, making it highly concise and well-structured.

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

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

Given the tool has no parameters, an output schema exists, and no annotations, the description is reasonably complete for a simple listing operation. It specifies the scope ('every account across every linked institution') and data source ('local cache'), though it could benefit from mentioning output format or caching implications for full completeness.

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

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

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the inputs. The description adds no parameter-specific information, but this is acceptable as there are no parameters to describe, aligning with the baseline 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 action ('List every account') and resource ('across every linked institution'), specifying it operates on data from the local cache. This distinguishes it from siblings like get_balances_tool or get_holdings_tool, which focus on specific data types rather than a comprehensive account listing.

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 broad overview of all accounts is needed, but does not explicitly state when to use it versus alternatives like list_linked_institutions_tool or get_balances_tool. It provides clear context by mentioning 'from the local cache', which suggests it retrieves cached data rather than real-time updates.

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 states the tool lists debts but does not disclose behavioral traits such as whether it requires authentication, how results are formatted, if there are rate limits, or if it's a read-only operation. The description is minimal and lacks essential context 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, efficient sentence that front-loads the purpose without waste. It is appropriately sized for a tool with no parameters, making every word count.

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 0 parameters and no annotations or output schema, the description is complete in stating what the tool does. However, it lacks details on behavioral aspects like return format or error handling, which are important for a tool with no structured output documentation. It meets minimum viability but has 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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description does not add parameter details, which is appropriate. Baseline is 4 for 0 parameters, as it avoids unnecessary information.

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

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

The description clearly states the specific action ('List every') and resource ('external (non-Plaid-linked) debt'), with precise scope ('the user has recorded'). It distinguishes from siblings like 'get_liabilities_tool' by specifying 'external' and 'non-Plaid-linked', avoiding tautology.

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

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

The description implies usage for retrieving external debts only, but does not explicitly state when to use this tool versus alternatives like 'get_liabilities_tool' or 'summarize_debt_tool'. No exclusions or prerequisites are mentioned, leaving some ambiguity.

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 discloses that the tool lists institutions with account counts and errors, which is useful behavioral context, but does not cover aspects like permissions, rate limits, or response format details beyond what the output schema might 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 a single, efficient sentence that front-loads the core purpose ('List every institution currently linked') and adds specific details ('with account counts and any errors') without any 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 low complexity (0 parameters, no annotations, but with an output schema), the description is reasonably complete. It specifies what is listed and additional details like account counts and errors, though it could benefit from more behavioral context given the lack of annotations.

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 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, which is appropriate, earning a baseline score above 3 due to the zero-parameter context.

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 specific action ('List every institution currently linked') and resource ('institution'), distinguishing it from siblings like 'list_accounts_tool' or 'remove_institution_tool' by focusing on linked institutions with account counts and errors.

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

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

The description implies usage for retrieving linked institutions with account details and errors, but does not explicitly state when to use this tool versus alternatives like 'list_accounts_tool' or 'remove_institution_tool', nor provide exclusions or prerequisites.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('List every account APR override') but lacks details on permissions required, data format returned, pagination, rate limits, or error conditions. This is a significant gap for a tool that likely accesses sensitive financial data.

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

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

The description is a single, efficient sentence that directly states the tool's purpose without any fluff or redundant information. It's appropriately sized and front-loaded, making it easy to understand at a glance.

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

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

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what an 'APR override' entails, the format of the returned data, or any behavioral aspects like data freshness or access controls. For a financial data tool with no structured metadata, this leaves critical gaps for an AI agent.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, earning a baseline score of 4 for not adding unnecessary information 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 ('List') and resource ('account APR override'), specifying that it retrieves every override recorded by the user. It distinguishes from siblings like 'set_account_override_tool' and 'clear_account_override_tool' by focusing on listing rather than modifying, though it doesn't explicitly differentiate from other list tools like 'list_accounts_tool'.

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. While it implies usage for viewing APR overrides, there's no mention of prerequisites, timing, or comparison with related tools like 'get_balances_tool' or 'get_liabilities_tool' that might overlap in financial data 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?

With no annotations provided, the description carries full burden and does an excellent job disclosing behavioral traits: it explains the asynchronous nature, timing expectations (30-60s wait), dependency on another tool (sync_transactions), and limitations ('some smaller banks don't support on-demand refresh'). Only minor gap: doesn't mention error handling or rate limits.

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?

Perfectly structured and front-loaded: first sentence states core purpose, subsequent sentences provide essential context. Every sentence earns its place with no wasted words. Four concise paragraphs cover purpose, usage, workflow, and parameter semantics efficiently.

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 no annotations, no output schema, and 0% schema coverage, the description provides excellent context about behavior, timing, dependencies, and limitations. It explains the asynchronous workflow clearly. Could be 5 with more detail about return values or error cases, but given the tool's relative simplicity, this is highly 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 0%, so the description must compensate. It clearly explains the semantics of the single parameter: 'Pass item_id to refresh one institution, or leave empty to refresh everything.' This adds crucial meaning beyond the schema's basic type information. Could be 5 with more detail about item_id format or examples.

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 with specific verbs ('nudge Plaid to pull fresh transactions') and identifies the resource ('transactions from the bank'). It distinguishes this tool from siblings like 'sync_transactions_tool' by explaining this triggers the data pull while sync_transactions ingests 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?

Explicitly states when to use ('when a user just made a purchase and wants to see it, or when transactions look stale') and when not to use ('Plaid normally refreshes on its own every few hours'). Provides clear alternative guidance ('wait 30-60s then call sync_transactions to ingest any new data').

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Delete' which implies a destructive mutation, but doesn't specify whether this is permanent, reversible, requires specific permissions, or has side effects (e.g., affecting linked data). This is a significant gap for a mutation tool with zero annotation coverage.

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

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

The description is a single, direct sentence with zero wasted words—'Delete an external debt entry.' It's front-loaded with the core action and resource, making it highly efficient and easy to parse. Every word 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?

Given the tool's complexity (a destructive mutation with no annotations, no output schema, and 1 undocumented parameter), the description is incomplete. It lacks crucial details like behavioral traits (e.g., permanence, permissions), parameter semantics, and expected outcomes, making it inadequate for safe and effective use by an AI agent.

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

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

The input schema has 1 parameter (debt_id) with 0% description coverage, meaning the schema provides no semantic context. The tool description doesn't add any parameter information—it doesn't explain what 'debt_id' represents, its format, or where to obtain it. This fails to compensate for the low schema coverage, leaving the parameter undocumented.

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 'Delete an external debt entry' clearly states the action (delete) and target resource (external debt entry), which is specific and unambiguous. However, it doesn't explicitly distinguish this from sibling tools like 'update_external_debt_tool' or 'list_external_debts_tool', which would be needed for a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives. For example, it doesn't mention prerequisites (e.g., needing an existing debt entry), exclusions, or how it differs from related tools like 'update_external_debt_tool' or 'remove_institution_tool'. This leaves the agent with minimal context for decision-making.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'delete its local data', implying a destructive operation, but lacks details on permissions required, whether the action is reversible, or any side effects like impact on related accounts or transactions.

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

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

The description is a single, efficient sentence that is front-loaded with the core action, with no unnecessary words or redundancy, making it easy to parse quickly.

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

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

Given the tool's destructive nature, lack of annotations, no output schema, and 0% schema coverage, the description is incomplete. It should address behavioral risks, parameter details, and expected outcomes to adequately guide an agent in a financial data 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 description coverage is 0%, and the description does not add any meaning beyond the schema. It does not explain what 'item_id' represents (e.g., a Plaid item identifier for the institution) or where to obtain it, leaving the single parameter undocumented.

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 with specific verbs ('unlink' and 'delete') and identifies the resource ('institution/Plaid item'), distinguishing it from sibling tools like 'list_linked_institutions_tool' or 'link_account' that handle listing or adding institutions.

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 whether it should be used for cleaning up old data or in error scenarios, nor does it mention prerequisites like needing a valid 'item_id' from a linked institution.

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

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

With no annotations provided, the description carries full burden but only states the search behavior ('fuzzy search'). It lacks details on permissions, rate limits, response format (though output schema exists), or side effects. For a search tool with 4 parameters, this minimal disclosure is inadequate for informed use.

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

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

The description is a single, efficient sentence with zero wasted words, front-loading the core functionality. It's appropriately sized for a basic tool description, though its brevity contributes to gaps in other dimensions.

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 4 parameters with 0% schema coverage and no annotations, the description is incomplete—it doesn't explain parameters or behavioral context. However, the presence of an output schema mitigates the need to describe return values. The tool is relatively simple (search function), so the description is minimally viable 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 0%, so the description must compensate but only implies 'query' for search. It doesn't explain 'start_date', 'end_date', or 'limit' parameters, their formats, or how they interact with the fuzzy search. The description adds minimal value beyond the bare schema, failing to address the coverage gap.

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 ('fuzzy search') and target resources ('transaction description and merchant name'), making the purpose understandable. It doesn't explicitly differentiate from sibling tools like 'get_transactions_tool' or 'search_transactions_tool' (if present), but the search focus is specific enough for basic clarity.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'get_transactions_tool' or 'refresh_transactions_tool'. It mentions 'fuzzy search' but doesn't specify scenarios where this is preferred over exact matches or other filtering methods, leaving usage context implied at best.

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 discloses key behavioral traits: it's a write operation ('annotate', 'record'), affects future analysis ('so summarize_debt_tool can reason honestly'), and has temporal effects ('After the promo_expires date, payoff analysis reverts'). It doesn't mention permissions or side effects, but covers the core mutation behavior well.

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

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

The description is appropriately sized and front-loaded: the first sentence states the core purpose, followed by specific examples and downstream effects. Every sentence adds value—no wasted words—and the structure flows logically from problem to solution to implications.

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 (mutation with temporal effects), no annotations, and no output schema, the description is largely complete. It explains the what, why, and how, including interactions with 'summarize_debt_tool'. It could mention error cases or confirmation of success, but covers the essential context well for a tool with 4 parameters.

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 0%, so the description must compensate. It explains the purpose of 'effective_apr' ('record the true effective APR') and 'promo_expires' ('optionally a promo expiration date'), adding meaning beyond the schema. It doesn't detail 'account_id' or 'note', but provides enough context for the critical parameters given the low 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 tool's purpose: 'Annotate a linked card with the real APR when Plaid misses it.' It specifies the verb ('annotate'), resource ('linked card'), and context ('when Plaid misses it'), distinguishing it from siblings like 'summarize_debt_tool' or 'get_liabilities_tool' by focusing on manual correction of data.

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

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

The description provides explicit guidance on when to use this tool: 'Common case: Citi doesn't consistently report 0% intro / balance-transfer promos through /liabilities/get.' It also states the alternative ('reverts to Plaid's reported purchase APR') and links to 'summarize_debt_tool' for downstream effects, making usage clear relative to other 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 the full burden of behavioral disclosure. It states what the tool does (aggregation) but doesn't describe any behavioral traits such as whether it's read-only, requires authentication, has rate limits, returns paginated results, or what happens with invalid inputs. For a tool with 3 parameters and no annotation coverage, 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?

The description is extremely concise - a single sentence with no wasted words. It's front-loaded with the core purpose and efficiently lists grouping options. Every element earns its place, making it easy to parse quickly.

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

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

Given the tool has 3 parameters with 0% schema coverage and no annotations, but does have an output schema, the description is moderately complete. The output schema reduces the need to describe return values, but the description should do more to explain parameter usage and behavioral context for this aggregation operation.

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

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

The input schema has 0% description coverage, so the description must compensate. It mentions grouping options (category, subcategory, merchant, account) which partially explains the 'group_by' parameter, but doesn't clarify the 'start_date' and 'end_date' parameters at all. The description adds some value for one parameter but leaves two completely unexplained.

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: 'Aggregate spending by category | subcategory | merchant | account.' It specifies the verb (aggregate) and resource (spending), and the grouping options provide some specificity. However, it doesn't explicitly distinguish this from sibling tools like 'get_transactions_tool' or 'search_transactions_tool' that might also retrieve spending data.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when this aggregation tool is preferred over transaction listing tools, nor does it specify any prerequisites or exclusions. The user must infer usage 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?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it merges data from Plaid and user inputs, ranks debts by strategy, and returns projections and warnings. However, it lacks details on permissions, rate limits, or error handling, which are important for a tool processing financial data.

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

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

The description is appropriately sized and front-loaded, starting with the core purpose. Every sentence adds value, such as explaining data sources, strategies, and outputs. It could be slightly more structured with bullet points for clarity, but it avoids redundancy and waste.

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

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

Given the complexity (financial projections with multiple inputs) and no annotations or output schema, the description is fairly complete. It covers purpose, parameters, and return values (balance, interest, projections, warnings). However, it lacks details on output format or error cases, which would enhance completeness for an agent.

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

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

Schema description coverage is 0%, so the description must compensate. It effectively explains all three parameters: 'strategy' (avalanche vs. snowball with definitions), 'extra_monthly_payment' (dollars above minimum), and implicitly 'today' (used for projections, though not explicitly named). This adds significant meaning beyond the bare schema.

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

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

The description clearly states the tool's purpose: 'Rank every debt and project payoff timelines.' It specifies the verb ('rank'), resource ('debt'), and scope ('project payoff timelines'), and distinguishes itself from sibling tools like 'get_liabilities_tool' or 'list_external_debts_tool' by focusing on ranking and projections rather than just listing or retrieving data.

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

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

The description provides clear context for when to use this tool: to analyze debt payoff strategies (avalanche vs. snowball) with extra payments. It implies usage for financial planning scenarios. However, it does not explicitly state when not to use it or name alternatives among siblings, such as 'get_liabilities_tool' for raw debt data without projections.

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 effectively describes key traits: idempotency, incremental syncing using cursors, asynchronous behavior for first syncs, blocking behavior with 'wait_for_ready', and the 'status' field indicating sync completion. It lacks details on rate limits or error handling, but covers essential operational aspects well.

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

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

The description is front-loaded with the core purpose in the first sentence, followed by critical behavioral details. Every sentence adds value: idempotency, cursor usage, first-sync behavior, parameter effects, and output field. There is no redundant or vague language, making it 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?

Given the complexity of syncing transactions with external APIs, no annotations, and no output schema, the description does well by covering purpose, key behaviors, and parameter effects. However, it lacks details on error cases, rate limits, or the exact structure of returned data (beyond the 'status' field), leaving some gaps for a fully informed agent.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the semantics of 'wait_for_ready' (controls blocking behavior during first sync) and implies 'wait_timeout_seconds' relates to timeout, though not explicitly. This adds meaningful context beyond the bare schema, but falls short of fully documenting both parameters, such as the exact role of the timeout.

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 specific action ('Pull the latest transactions from Plaid into the local cache'), identifies the resource (transactions from Plaid), and distinguishes it from siblings like 'get_transactions_tool' (which likely retrieves cached data) and 'refresh_transactions_tool' (which might force a full refresh). The mention of 'idempotent and incremental' further clarifies its operational scope.

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 on when to use this tool: for syncing transactions from Plaid, particularly noting its behavior during 'first sync after linking an institution' and the effect of the 'wait_for_ready' parameter. However, it does not explicitly state when not to use it or name alternatives like 'refresh_transactions_tool' for comparison, which prevents a perfect score.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is an update operation, implying mutation, but doesn't disclose any behavioral traits like permission requirements, whether changes are reversible, rate limits, or what happens to fields not mentioned. For a mutation tool with 8 parameters, 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?

The description is a single, efficient sentence that communicates the core purpose without unnecessary words. It's appropriately sized and front-loaded with the essential information.

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

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

For a mutation tool with 8 parameters, 0% schema description coverage, no annotations, and no output schema, the description is inadequate. It doesn't explain what constitutes an 'external debt', what fields are updatable, what the response looks like, or any error conditions. The agent would struggle to use this tool effectively.

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

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

The description mentions updating 'fields' which maps to the 7 optional parameters in the schema, but doesn't provide any additional semantic meaning beyond what's implied by the parameter names. With 0% schema description coverage, the description doesn't compensate by explaining what each field represents, their formats, or constraints. The baseline is 3 since it at least acknowledges parameters exist.

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 ('update') and resource ('existing external debt'), and specifies it can update 'any subset of fields', which adds useful detail. However, it doesn't explicitly differentiate from sibling tools like 'remove_external_debt_tool' or 'list_external_debts_tool' beyond the basic verb difference.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'add_external_debt_tool' for creating new debts or 'remove_external_debt_tool' for deletion. It mentions 'existing external debt' which implies a prerequisite that the debt must already exist, but doesn't state this explicitly or reference other tools.

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