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

With no annotations, the description fully bears the burden of behavioral disclosure. It explains that no parameters triggers a show operation, any parameters triggers an update+reconnect, and omitted parameters keep current values. This is comprehensive for a configuration 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 well-structured with numbered steps and a bullet list, front-loading the main purpose. It is concise with no superfluous content, though the 'Args' section could be integrated more tightly, but it adds value with examples.

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

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

Given 5 optional parameters and no output schema, the description adequately covers the tool's behavior (show vs update, partial updates). It does not describe return values or error handling, but for a config tool, this is acceptable. A slightly higher score would require mention of response format.

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

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

Schema coverage is 0% (the description does not reference schema properties), but the 'Args' section in the description adds valuable meaning for each parameter with examples (e.g., host examples 'localhost', 'host.docker.internal', '72.212.424.42'). This compensates well for 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 configures the active Hummingbot API server connection. It distinguishes between showing current config (no params) and updating (with params), which is a specific verb+resource combination. Among sibling tools like 'explore_dex_pools' or 'manage_bots', this tool's purpose is unique and well-defined.

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 guidance on when to use the tool: no parameters to view current config, any parameters to update. It does not explicitly mention when not to use it or alternatives, but the sibling list doesn't contain obvious alternatives for config management, so the guidance is adequate.

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

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

With no annotations, the description carries full burden. It discloses that the tool is read-only (explore), lists supported actions, and mentions default values for parameters. However, it does not explicitly state side effects, rate limits, or authentication requirements. The lack of explicit read-only declaration is a minor 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 well-structured with bullet points and separate sections for actions, arguments, and cross-references. It front-loads the main purpose. However, some redundancy exists (e.g., repeating parameter details in the bullet list that are also in the schema), and the length could be trimmed slightly without losing 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?

Given the complexity (11 parameters, 2 actions, no output schema), the description is thorough. It covers usage instructions, parameter semantics, and references to sibling tools. All necessary information for correct invocation is present, with no 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% description coverage, so the description fully compensates by providing detailed explanations for all 11 parameters, including defaults and constraints (e.g., limit max 100). Each parameter's purpose and when it's required (e.g., network for get_pool_info) are clearly described.

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 explores DeFi CLMM pools, lists pools, and gets pool details. It distinguishes from siblings by referencing 'manage_executors' for LP positions and 'get_portfolio_overview' for on-chain positions, making the tool's specific role unambiguous.

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

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

The description explicitly explains when to use each action (list_pools vs get_pool_info) and provides cross-references to sibling tools for related tasks (LP management, portfolio overview). It also lists supported DEX connectors, giving clear 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. It states the tool is 'free, no API key needed' and outlines the action flow. However, it does not explicitly confirm read-only behavior, error handling, rate limits, or the impact of invalid parameters. The behavioral disclosure is adequate but not exhaustive.

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: an opening sentence, a numbered action list, then parameter definitions. It is front-loaded with the core purpose. While lengthy due to the number of actions, each sentence is necessary and earns its place. Minor redundancy could be trimmed, but overall it is efficient.

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

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

Given the complexity (12 parameters, 11 actions, no output schema), the description covers the tool's functionality comprehensively. It details all actions, required parameters, and optional arguments like timeframe and pagination (before_timestamp). It does not explain the return format, but that is acceptable without an output schema. Overall, it provides sufficient context for an agent to use 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, so the description must compensate. It explains all 12 parameters with examples and default values (e.g., 'network: Network ID (e.g., solana, eth). Required for most actions.'). This adds significant meaning beyond the raw schema, though some parameters like 'token' could benefit from more context about allowed values.

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: 'Explore DEX market data from GeckoTerminal'. It enumerates 11 distinct actions, each with a brief description, making the capabilities concrete and easy to understand. The name and description together unambiguously identify the tool's scope and resource.

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 progressive discovery flow and details when to use each action. However, it does not explicitly guide the agent on when to choose this tool over sibling tools like explore_dex_pools. Usage context is implied through the action list but lacks direct comparison or exclusion criteria.

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

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

With no annotations, the description bears full burden. It discloses that the tool reads market data and specifies which parameters are required for each data type. It does not mention side effects or rate limits, but it is clear that the tool is read-only. The structure provides good insight into behavior.

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

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

The description is well-structured with clear headings and bullet points, front-loading the purpose. It is detailed but not overly verbose; every sentence adds value. Minor redundancy (e.g., repeating enum options) but overall efficient.

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

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

Given the complexity (9 params, no output schema), the description covers all data types and their necessary parameters. It does not describe return format or pagination, but for a read tool, this is adequate. It provides enough context for an agent to select and use 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 description adds significant meaning beyond the schema: it explains which parameters are required for each data type, provides examples, and defines enumeration options (e.g., interval choices, query types). Since schema coverage is 0%, this fully compensates and is essential 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 clearly states the tool retrieves market data (prices, candles, funding rates, order book) and enumerates each data type with a specific verb (e.g., 'Get latest prices'). This is explicit and distinguishes the tool from siblings focused on other domains like DEX pools or portfolio overview.

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 explains what each data type does but does not provide when-to-use advice or comparison to alternatives (e.g., when to use this vs explore_dex_pools). It implies usage through the listed data types but lacks explicit guidelines on 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?

No annotations are provided, so the description carries full burden. It discloses key behavioral traits: fetching data in parallel with asyncio.gather, querying multiple sources, database queries for LP positions, real-time data retrieval, and refresh vs cached behavior. This provides meaningful context beyond what annotations would convey.

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 moderately long but well-structured with a clear overview, data source list, and parameter section. Every sentence serves a purpose, though it could be slightly more concise by merging the data source list with the parameter descriptions. It remains informative without being verbose.

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

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

Given the complexity (8 parameters, no output schema, no annotations), the description is highly complete. It explains the data sources, filtering options, refresh behavior, and historical data separation. The only minor gap is the lack of output format description, but this is acceptable without an output schema.

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 does so excellently by explaining each parameter (account_names, connector_names, include_balances, etc.), their defaults, and their effects. For example, it clarifies that 'include_lp_positions' triggers database queries and real-time blockchain calls. This adds significant value beyond the raw 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 provides a 'unified portfolio overview' with specific data types (balances, perpetual positions, LP positions, active orders). It distinguishes itself from sibling tool search_history by noting this shows only active/open positions, while search_history handles historical 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 explains when to use the tool (for a comprehensive portfolio overview) and explicitly directs users to search_history for historical data. It also details filtering options like account_names and connector_names. However, it does not cover all sibling tools or provide a comprehensive decision tree.

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

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

With no annotations, the description carries full burden. It details each action's behavior, including destructive actions like stop_bot (stops and archives forever) and update_config requiring confirm_override. However, it could more explicitly state reversibility for actions like stop_controllers.

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-organized with sections for general purpose, usage guidance, actions with bullet points, and parameter descriptions. It is front-loaded with key information and concise 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 14 parameters, no annotations, and no output schema, the description covers all actions and their parameter dependencies, including defaults. It provides complete guidance for the agent to use 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 description explains each action's required parameters beyond the input schema, which has 0% coverage. It adds details like config_data must include 'controller_type' and 'controller_name', log_type enum options, and defaults for account_name and image.

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 as managing controller-based bots with specific actions like deploy, monitor, logs, control execution, and config modification. It distinguishes from sibling tools like manage_executors by explicitly noting when to use bots vs. executors.

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 when-to-use and when-not-to-use guidance, recommending manage_executors for most trading strategies and only using bots when the user explicitly asks for 'bot' deployment or needs advanced features. It names the alternative sibling 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?

With no annotations, the description carries full burden. It discloses that the tool works with design-time items and does not affect running bots. However, it omits potential destructions (e.g., deleting controllers) and authorization needs, though this is partially mitigated by the note about confirm_override.

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 long but well-structured: it front-loads key information, uses numbered flows, and separates concerns. A bit verbose, but the organization justifies the length.

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 9 parameters, no annotations, and no output schema, the description is remarkably complete. It covers purpose, usage, parameter details, enum values, and alternatives, providing an agent with all necessary context 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?

Schema coverage is 0%, but the description compensates extensively. It explains each action-target combination, provides example flows, and documents common enum values (position_mode, side, order_type) with numeric requirements, far exceeding schema 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 it manages controller templates and saved configurations at design-time. It explicitly distinguishes itself from sibling tools like manage_bots (for live bot configs) and manage_executors (for most trading strategies), ensuring correct tool selection.

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 (for controllers, bots, advanced multi-strategy deployments) and when not to (for most strategies, use manage_executors). It also details the exploration and modification flows, offering clear instructions.

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

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

With no annotations, the description carries the full burden. It describes many behaviors: progressive disclosure for executor types, default merging with saved defaults, pagination with cursor and limit, stop with keep_position option, and log retrieval only for active executors. It does not mention rate limits or authentication requirements, but covers core behavioral traits 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 verbose but well-structured with headings, bullet points, and clear sections. It front-loads the main purpose and then details actions and parameters. Every sentence provides useful information. However, it could be more concise; the list of executor types and actions could be summarized.

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 (18 parameters, multiple actions, no output schema, no annotations), the description is remarkably complete. It covers all actions, parameters, defaults, executor types, and even references sibling tools (explore_dex_pools). It explains progressive disclosure and preferences management comprehensively.

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

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

Schema coverage is 0%, so the description must compensate. It explains every parameter in the Args list, including defaults (e.g., limit default 50, keep_position default false). It clarifies action-specific requirements (e.g., 'executor_config required for create'). Some parameters like 'cursor' and 'log_level' are explained sufficiently. The description adds significant meaning beyond the schema.

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

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

The description clearly states the tool's purpose: 'Manage trading executors: create, search, stop, and configure preferences.' It explicitly labels itself as the 'DEFAULT tool for ALL trading operations,' which distinguishes it from sibling tools like manage_bots or manage_controllers. The listing of executor types and actions provides specific context.

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

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

The description gives explicit instructions: 'Use progressive disclosure to get the full guide and config schema for any executor type before creating.' It explains when to use different actions (e.g., 'executor_type with no action → Show full guide'). However, it does not explicitly state when NOT to use this tool or provide clear comparisons with 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?

No annotations provided, so description must disclose behavior. It implies read-only nature but does not explicitly state lack of side effects, rate limits, or permissions. Some context is given but not comprehensive.

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?

Description is structured into sections with clear headings and examples. It is reasonably concise given the number of parameters, though slightly verbose in places.

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

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

Given no output schema and no annotations, the description provides sufficient context for an agent to select and invoke the tool. It covers data types, filters, and usage examples, though return format and errors are omitted.

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

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

Schema coverage is 0%, but description compensates by listing and explaining each parameter with context, including examples and default values. However, some parameters (e.g., account_names) are less detailed.

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 searches historical data and lists three specific data types. It also distinguishes from sibling tool get_portfolio_overview by noting it is for real-time 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?

Explicitly advises using get_portfolio_overview for real-time queries instead. Provides detailed information on data types and filters, guiding appropriate 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?

With no annotations, the description fully explains the tool's behavior: it can set one or both settings depending on provided parameters. It also notes the dependency of trading_pair for leverage and position_mode for HEDGE mode. No contradictions.

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 clear purpose sentence followed by conditional logic and parameter descriptions. It uses a docstring style. While it could be more concise, each sentence adds value and it remains readable.

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 enums, and no output schema, the description covers all relevant aspects: parameter roles, conditional requirements, and default values. It is fairly complete for an agent to understand when and how to call the tool.

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

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

Schema coverage is 0%, so the description must add meaning. It explains defaults (account_name default 'master_account'), valid values for position_mode ('HEDGE' or 'ONE-WAY'), and context for trading_pair and leverage. This goes beyond the raw 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 it sets position mode and leverage for an account on a specific exchange. It also explains conditional behavior (if one param missing, only sets the other), which distinguishes it from any sibling tools that might perform related but different configuration tasks.

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 explains when each parameter is used (e.g., trading_pair only for leverage, position_mode optional) and the conditional logic. However, it does not explicitly compare to alternative tools or provide guidance on when to choose this tool over others.

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 thoroughly explains the multi-step flow, including override confirmation and the two actions. The behavioral traits (progressive disclosure, error handling via account selection) are well disclosed.

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 numbered steps and bullet points, front-loading the purpose. However, it is somewhat lengthy and repeats information (e.g., the args section echoes the step list). Could be slightly more concise, but still 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 the complexity of the tool (5 parameters, interactive flow) and no output schema, the description covers the process adequately. It lacks information about return values or error handling after each step, but for a setup tool the flow is detailed enough.

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%, but the description compensates by explaining each parameter's role in the flow. For example, 'action' is described with its possible values, and 'credentials' is related to required fields. All 5 parameters are covered with 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 it is for setting up or deleting exchange connectors with a progressive disclosure approach. It distinguishes between the two flows and provides a specific verb+resource. Compared to sibling tools like configure_server or manage_bots, it uniquely handles exchange connector management.

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

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

The description provides explicit step-by-step guidance for both setup and delete flows, indicating when to use each parameter. It implicitly tells when to use the tool (for connecting an exchange) but does not explicitly state when not to use it or mention alternatives. However, the progressive disclosure is a strong guideline.

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