Harris Boat Works - Mercury Repower

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

With no annotations, the description reveals the tool returns a deep-link URL and optionally captures a lead (a side effect). However, it does not disclose whether the quote is persisted, idempotency, rate limits, or auth requirements. The side effect is mentioned but understated.

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

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

Two sentences front-load the core purpose and return type. The second sentence adds optional contact handling. Could be slightly more structured by separating the components list from the lead capture, but still short and mostly 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 7 parameters including nested objects and no output schema, the description is too brief. It does not explain the purpose of each parameter (e.g., 'family', 'horsepower'), what the deep-link URL enables, or what happens on failure. The completeness is inadequate for an agent to reliably invoke 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 description coverage is 0%, so the description must explain parameters. It lists components like 'propeller' and 'financing tier' that do not directly map to any schema properties (e.g., missing from schema parameters). Key parameters like 'family', 'boat_info', and 'horsepower' are not explained, leaving much ambiguity.

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 builds an itemized CAD quote listing explicit components (motor, installation, etc.) and returns a deep-link URL. This distinguishes it from siblings like estimate_trade_in or search_motors which focus on subtasks.

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 use for building a complete quote, but does not explicitly state when to use this vs. alternatives or provide conditions like prerequisites or when not to use. The mention of optional CRM lead capture hints at a specific use case but lacks clarity.

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

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

No annotations are provided, so the description bears the full burden. It mentions brand penalties (Mercury preferred, others discounted) but does not disclose how condition, engine type, or engine hours affect the estimate. It does not state whether the operation is read-only or if any destructive changes occur. The behavioral disclosure is incomplete.

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

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

The description is concise at two sentences, with the primary action in the first sentence and behavioral detail in the second. It is front-loaded and has no wasted words. However, it could be structured to list key parameters or usage notes.

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, no annotations, and 6 parameters, the description is too brief. It does not explain what the estimate returns (e.g., a dollar amount, range), any prerequisites (customer info needed), or how the tool handles missing parameters like condition. More detail is needed for an agent to confidently invoke it.

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% coverage, so the description must compensate. It mentions brand, year, and horsepower implicitly through the brand penalties context, but does not explain condition, engine_type, or engine_hours. The allowed values for enums (condition, engine_type) are not described. The description adds some meaning but is insufficient to fully understand parameter usage.

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 purpose is clear: 'Estimate the trade-in value (CAD) of a customer's current outboard.' The verb 'estimate' and resource 'trade-in value' are specific. The description mentions brand penalties, which adds context but does not explicitly differentiate from sibling tools like build_quote or search_motors. However, the purpose is distinct enough that an agent would likely select this tool for trade-in estimation.

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

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

No usage guidelines provided. The description does not state when to use this tool versus alternatives (e.g., for current outboard trade-ins, not for new quotes). There is no exclusion criteria or context about when not to use it.

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

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

No annotations, but description fully discloses what the tool returns (authoritative rules list) without omissions. No mention of side effects or auth, but for a zero-param read tool, this is adequate. Could note non-destructive nature.

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

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

Single sentence, front-loaded with key info, no fluff. 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 zero parameters, no output schema, and simple purpose, description is fully complete. Sibling tools confirm distinct operations.

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

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

No parameters. Baseline is 4. Description adds context by listing what rules are returned, providing meaning beyond the empty schema.

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

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

Description uses specific verb 'Return' and resource 'Harris Boat Works' authoritative source-of-truth rules', listing exact categories (pricing, geography, no-Verado policy, etc.). Clearly distinguishes from sibling tools like build_quote or search_motors.

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

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

No explicit when/when-not or alternatives mentioned. However, the description implies usage for retrieving brand rules, and sibling list provides implicit differentiation. Lacks direct guidance like 'use this instead of X'.

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 only describes the operation as a fetch and lists returned fields, but does not disclose behavior like selection logic when both id and slug are provided, authentication needs, 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?

The description is a single, well-structured sentence that is front-loaded with the action and resource. It contains no unnecessary words or repetitions.

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

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

The description lists a few return fields but does not provide a complete view of the output structure. Without an output schema, the agent may miss other important fields in the response. For a simple fetch, it is adequate but incomplete.

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

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

Schema coverage is 100% (both parameters described in schema). The description reinforces that either id or slug can be used, but adds no additional semantic meaning beyond what the schema already provides.

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

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

The description uses a specific verb ('Fetch') and resource ('single Mercury motor'), and distinguishes itself from sibling tools like search_motors (which likely returns multiple) by focusing on individual retrieval by id or slug. It clearly states what data is included.

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 does not explicitly state when to use this tool versus siblings (e.g., search_motors). It implies use when a single motor's details are needed, but lacks guidance on 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, the description carries full burden. It discloses non-obvious behaviors (CAD pricing, Verado exclusion) but does not mention pagination, response format, or behavior on empty results.

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

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

Two sentences, no extraneous words, front-loaded with key information. Every sentence is essential.

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

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

Given 6 parameters with 0 required, no output schema, and no annotations, the description provides reasonable coverage of purpose and main filters but lacks details on parameter interactions (e.g., min_hp vs max_hp vs horsepower) and result handling.

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 low (17%), but the description lists key filtering dimensions (horsepower, family, stock status). However, it does not explain parameters like limit, min_hp, or max_hp beyond the schema defaults.

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

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

The description clearly states it searches Mercury outboard inventory at a specific dealer (Harris Boat Works) with filters. It distinguishes from siblings like get_motor and build_quote.

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 filters are available and mentions CAD pricing and Verado exclusion, but does not explicitly state when to use versus alternative tools. However, the context from sibling names provides implicit guidance.

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