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 successfully indicates this is a mutation operation ('Add products') and mentions batch capability ('multiple items at once'), but doesn't address important behavioral aspects like error handling, idempotency, permissions needed, or what happens when adding duplicate items. The description adds some value but leaves significant gaps.

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

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

The description is efficiently structured with a clear purpose statement followed by bullet points for item details and a final sentence providing usage context. Every sentence earns its place, with no redundant information or unnecessary elaboration. The bullet format enhances readability without sacrificing conciseness.

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

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

For a mutation tool with no annotations and no output schema, the description provides adequate basic information about what the tool does but lacks important contextual details. It doesn't describe the return value format, error conditions, or system behavior when items are added. The description is complete enough for basic understanding but insufficient for robust agent operation without additional trial-and-error learning.

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 100% schema description coverage, the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by listing the same four item fields with slightly different wording, but doesn't provide additional semantic context like examples of valid product names beyond what's in the schema or clarification about barcode format requirements.

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 ('Add products') and target resource ('to an existing shopping list'), distinguishing it from sibling tools like 'create_shopping_list' (creates new lists) and 'optimize_shopping_list' (modifies existing lists differently). The verb+resource combination is precise and unambiguous.

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

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

The description provides clear context for when to use this tool ('Perfect for building up your shopping list before optimizing'), which implicitly suggests it should be used before the 'optimize_shopping_list' sibling tool. However, it doesn't explicitly state when NOT to use it or name specific alternatives for similar operations.

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 describes what the tool provides (lowest price, highest price, average, savings, differences) but doesn't disclose behavioral traits like whether it requires authentication, rate limits, data freshness, or error conditions. The description adds value by outlining outputs but misses key operational context.

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

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

The description is appropriately sized and front-loaded with the core purpose in the first sentence. The bulleted list efficiently details outputs, and the final sentence reinforces use case. Minor redundancy exists (e.g., 'find the best deal' and 'best deals'), but overall structure is clear with minimal 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 no annotations and no output schema, the description partially compensates by listing output details. However, for a tool with 2 parameters and complex price comparison logic, it lacks completeness regarding behavioral constraints (e.g., data sources, update frequency) and error handling. It's adequate but has clear gaps in operational 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?

Schema description coverage is 100%, providing clear parameter documentation. The description doesn't add meaning beyond the schema (e.g., it doesn't explain how 'productName' matching works or 'maxResults' implications). With high schema coverage, baseline 3 is appropriate as the description doesn't compensate but doesn't detract either.

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 ('compare prices', 'find the best deal') and resources ('product across all supermarkets'). It distinguishes from siblings like 'get_best_deals' by focusing on price comparison for a specific product rather than general deals, and from 'search_products' by emphasizing comparative analysis rather than basic search.

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 context ('perfect for making informed buying decisions') but doesn't explicitly state when to use this tool versus alternatives like 'get_best_deals' (which might show deals without product-specific comparison) or 'search_products' (which might return product info without price analysis). No explicit exclusions or prerequisites are provided.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the tool creates lists and includes features like linking to user IDs, it lacks critical behavioral details such as permission requirements, whether creation is idempotent, error conditions, or what the response contains. For a creation tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.

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 and appropriately sized, starting with a clear purpose statement followed by usage flexibility and a bulleted feature list. While the bullet points are helpful, the second sentence about supermarket optimization feels slightly tangential and could be more tightly integrated with the core functionality.

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 (creation with optional nested items), no annotations, and no output schema, the description is partially complete. It covers the basic purpose and parameters but lacks behavioral transparency and output details. For a creation tool, it should ideally mention what happens on success (e.g., returns list ID) or failure, making it adequate but with clear gaps.

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

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

The description adds some semantic context beyond the schema, such as explaining the purpose ('organize your purchases') and listing features that map to parameters (e.g., 'include initial items with quantities'). However, with 100% schema description coverage, the schema already documents all parameters thoroughly, so the description provides only marginal additional value without explaining parameter interactions 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 with specific verbs ('create a new shopping list') and resource ('shopping list'), distinguishing it from siblings like 'get_shopping_lists' (read) and 'remove_shopping_list' (delete). It explicitly mentions creating both empty lists and lists with initial items, making the scope unambiguous.

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

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

The description provides clear context on when to use this tool ('useful for planning your shopping'), including the flexibility to create empty lists or lists with items. However, it doesn't explicitly state when NOT to use it or mention alternatives like 'add_items_to_list' for adding items to existing lists, which would be helpful for sibling differentiation.

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 and does this well. It reveals key behavioral traits: the tool calculates distances using the Haversine formula, provides distance in km/meters, returns addresses and contact info, includes opening hours when available, and has a default search radius of 5km. It doesn't mention rate limits, authentication needs, or data freshness concerns.

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 front-loaded with the core purpose, but contains some redundancy and marketing language that doesn't earn its place. Sentences like 'Discover which supermarkets are closest to you!' and the 'Perfect for' bullet points add little operational value. The Haversine formula explanation is useful but could be more concise. Overall structure is logical but could be tighter.

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, no annotations, and no output schema, the description provides good contextual completeness. It explains what the tool does, how it works (Haversine formula), what information it returns (addresses, contact info, opening hours, distances), and includes practical examples. The main gap is the lack of output format specification, which would be helpful given no output schema exists.

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

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

Schema description coverage is 100%, so the schema already fully documents all three parameters (latitude, longitude, radiusKm). The description adds minimal value beyond the schema - it mentions 'Search by latitude and longitude' and 'Customizable search radius (default: 5km)' but provides no additional semantic context about parameter usage or implications. The example coordinates are helpful but don't fundamentally enhance 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 ('Find supermarkets near your current location') and resource ('supermarkets'), distinguishing it from sibling tools like 'search_products' or 'get_best_deals' which focus on products/deals rather than physical store locations. It explicitly mentions using GPS coordinates for location-based searching.

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 ('Finding nearby stores after optimizing your shopping list', 'Planning your shopping route', 'Discovering new supermarkets in your area'), but doesn't explicitly state when NOT to use it or mention alternatives among the sibling tools. The 'Perfect for' section gives good usage scenarios without 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 the full burden. It mentions discovering deals but fails to disclose key behavioral traits such as whether results are real-time, how deals are ranked, if authentication is needed, or any rate limits. This is a significant gap for a tool with potential complexity in data sourcing and presentation.

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 a clear purpose statement followed by bullet points for specific features and a concluding use case. It avoids redundancy, though the bullet points could be slightly more concise, and every sentence contributes to understanding the tool's value.

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 does not explain what the tool returns (e.g., deal details, supermarket names, prices), how results are structured, or any limitations (e.g., geographic scope, data freshness). For a deal-finding tool with potential complexity, this leaves significant gaps for an AI agent 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 100%, so the schema already documents both parameters ('category' and 'maxResults') with clear descriptions and constraints. The description adds no additional parameter semantics beyond what the schema provides, such as examples of categories or context for maxResults, meeting the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose as finding best deals and discounts in supermarkets, specifying resources like products on sale and best price-to-value items. It distinguishes from siblings like 'compare_prices' or 'search_products' by focusing on curated deals rather than general price comparison or product search, though it could be more explicit about the distinction.

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 budget shopping and finding savings, suggesting when to use it (e.g., for deals rather than general product lookup). However, it lacks explicit guidance on when to use this versus alternatives like 'compare_prices' or 'search_products', leaving some ambiguity in tool 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 the full burden of behavioral disclosure. It describes what information is returned (current prices, target prices, triggered status, proximity to target, last check time), which is helpful. However, it lacks details on permissions, rate limits, pagination, or error handling, leaving gaps for a read operation.

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 and front-loaded with the core purpose, followed by bullet points for details and a 'Perfect for' section for usage context. Every sentence adds value without repetition, making it 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 no annotations and no output schema, the description does a good job explaining what the tool returns (e.g., current vs. target prices, triggered alerts). However, it could be more complete by specifying return format or data structure, especially 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 input schema has 100% description coverage, so the baseline is 3. The description adds value by implying default behavior ('Get all your active price alerts') and context for filtering, such as focusing on 'active' alerts and 'your' data, which complements the schema's optional parameters without redundancy.

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 ('Get all your active price alerts') and resource ('price alerts with their current status'), distinguishing it from siblings like 'set_price_alert' or 'remove_price_alert'. It explicitly defines the scope as 'your' alerts, making the purpose unambiguous.

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

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

The description provides clear context for when to use this tool ('Perfect for: Reviewing all your alerts, Finding triggered alerts, Managing your watchlist'), which helps differentiate it from tools like 'get_best_deals' or 'search_products'. However, it does not explicitly state when NOT to use it or name specific alternatives for overlapping functions.

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 that the tool 'Returns a list of all active shopping lists with their items,' which clarifies the output format and scope ('active'). However, it fails to disclose critical behavioral traits such as whether this is a read-only operation (implied but not stated), potential rate limits, authentication needs, or pagination handling. For a tool with zero annotation coverage, this is a significant gap, warranting a score of 2.

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 output details and a 'Useful for' section. Each sentence adds value, such as clarifying the return format and use cases. However, the bullet points could be more concise (e.g., 'Finding a specific list to optimize' is somewhat verbose), and there's minor redundancy in emphasizing 'all' lists. Overall, it's efficient but not perfectly streamlined, earning a score of 4.

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 (1 optional parameter, no output schema, no annotations), the description is moderately complete. It covers the purpose, output format, and use cases, but lacks details on behavioral aspects like safety (read-only vs. mutation) or error handling. Without annotations or output schema, the description should do more to compensate, such as explicitly stating it's a read operation or mentioning any limitations. This results in a score of 3, as it's adequate but has clear gaps for a tool with no structured support.

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 100% description coverage, with the parameter 'userId' documented as 'Optional: Filter lists by user ID.' The description adds value by reinforcing this optional filtering ('optionally filtered by user') and implying it returns 'all active shopping lists' when no filter is applied. However, it doesn't provide additional semantics beyond what the schema already covers, such as format details or examples. With high schema coverage, the baseline is 3, which is appropriate here.

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: 'Get all shopping lists, optionally filtered by user.' This specifies the verb ('Get') and resource ('shopping lists') with scope ('all'), and it distinguishes from siblings like 'create_shopping_list' or 'remove_shopping_list' by focusing on retrieval. However, it doesn't explicitly differentiate from potential list-viewing alternatives (e.g., 'get_my_alerts' might overlap in context), keeping it at 4 rather than 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 implied usage through 'Useful for' bullet points (e.g., 'Viewing all your saved lists'), which suggests contexts like management or optimization. However, it lacks explicit guidance on when to use this tool versus alternatives like 'search_products' or 'get_est_deals' for related tasks, and it doesn't specify exclusions or prerequisites. This results in a score of 3 for implied but incomplete 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the tool's actions (searching across all supermarkets, calculating total costs, showing savings) but lacks details on permissions, rate limits, error handling, or what happens if no supermarkets are active. For a tool that likely involves external API calls and calculations, 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 front-loaded with a clear purpose statement, but it includes repetitive elements (e.g., 'Perfect for' list could be condensed) and uses excessive formatting (🔥, ALL CAPS). Some sentences, like 'This is the most powerful feature', do not add essential information. It could be more streamlined while retaining key 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 complexity of a tool that searches across multiple supermarkets and calculates costs, with no annotations and no output schema, the description is moderately complete. It explains the tool's high-level behavior and benefits but lacks details on output format, error cases, or performance considerations. For a tool with significant computational and external dependencies, more context would be helpful.

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 100% description coverage, with the single parameter 'listId' documented as 'ID of the shopping list to optimize'. The description does not add any additional meaning beyond this, such as format examples or constraints. Since schema coverage is high, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't need to given the schema's clarity.

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 ('find the best supermarket', 'searches for every product', 'calculates the total cost') and distinguishes it from siblings like 'compare_prices' or 'find_nearby_supermarkets' by emphasizing optimization of an entire shopping list across all supermarkets. It explicitly mentions the resource (shopping list) and scope (all supermarkets in Argentina).

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 ('perfect for maximizing savings, planning where to shop, comparing complete shopping costs'), but it does not explicitly state when not to use it or name specific alternatives among siblings. It implies usage for entire shopping list optimization rather than individual product comparisons, which helps differentiate from tools like 'compare_prices'.

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 action 'permanently removes the alert', indicating irreversibility, and clarifies it stops monitoring. However, it lacks details on permissions needed, error conditions, or confirmation 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?

Three short, front-loaded sentences with zero waste: the first states the action, the second explains the effect, and the third warns of permanence. Each sentence adds critical information 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?

Given no annotations, no output schema, and a simple single-parameter input, the description is mostly complete for a deletion tool. It covers purpose and behavioral impact but could improve by mentioning error cases or success indicators.

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 100%, so the schema already documents the 'alertId' parameter. The description does not add specific parameter details beyond implying the alert exists, but with 0 parameters needing extra explanation, it meets the baseline of 4 for adequate 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 explicitly states the verb 'Delete' and resource 'price alert' in the first sentence, then elaborates with 'Stop monitoring a product's price' to clarify the action. It clearly distinguishes from sibling tools like 'set_price_alert' (create) and 'get_my_alerts' (read).

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 you want to stop monitoring a product's price, but does not explicitly state when to use this vs. alternatives like 'get_my_alerts' for viewing alerts or 'set_price_alert' for creating them. No exclusions or prerequisites are mentioned.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively explains that this is a destructive operation ('removes the list and all its items'), clarifies the deletion type ('soft-deleted'), and notes recoverability ('can be recovered if needed'). However, it lacks details on permissions, error conditions, or confirmation prompts.

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 two concise sentences that add critical behavioral context. Every sentence earns its place by clarifying scope and deletion behavior 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?

For a destructive tool with no annotations and no output schema, the description provides adequate basics (purpose and soft-delete behavior) but lacks completeness. It doesn't cover error handling, return values, or integration with sibling tools, leaving gaps for an agent to infer operational details.

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

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

The input schema has 100% description coverage, with the single parameter 'listId' clearly documented. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or constraints, but this is acceptable given the high schema coverage.

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

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

The description clearly states the specific action ('Delete a shopping list') and resource ('shopping list'), distinguishing it from siblings like 'create_shopping_list' or 'get_shopping_lists'. It goes beyond the tool name by specifying what gets removed ('the list and all its items from the active lists').

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. While it's clear this is for deletion, there's no mention of prerequisites (e.g., list must exist), recovery options, or when to choose this over other list-management tools like 'optimize_shopping_list'.

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 the core behavior (exact product matching across supermarkets) and outcome (price comparisons). However, it lacks details about rate limits, error conditions, authentication requirements, or what happens when no matches are found. The description doesn't contradict any annotations since none exist.

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

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

The description is well-structured with a clear opening statement followed by bullet points for use cases and a concluding sentence about outcomes. It's appropriately sized for the tool's complexity. However, the bullet points could be more concise, and some redundancy exists between 'finding exact product matches' and 'exact same product across different stores.'

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 single-parameter search tool with no annotations and no output schema, the description provides adequate context about what the tool does and when to use it. However, it doesn't describe the return format (what data comes back), error handling, or limitations. Given the lack of structured output documentation, more completeness would be beneficial.

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 100% description coverage, clearly documenting the single 'code' parameter as a numeric EAN/barcode. The description adds minimal value beyond the schema, only reinforcing that it searches by 'EAN/barcode' without providing additional format details or examples. This meets the baseline expectation when schema coverage is complete.

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 ('search for a specific product') and resource ('by its EAN/barcode across all supermarkets'). It explicitly distinguishes this tool from sibling tools like 'search_products' by focusing on exact barcode-based matching rather than general product searches.

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 ('perfect for finding exact product matches, scanning barcodes, price checking specific items, verifying product availability'). It distinguishes from 'search_products' by emphasizing exact matching across stores. However, it doesn't explicitly state when NOT to use it or mention specific alternatives like 'compare_prices' for broader comparisons.

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: it searches multiple supermarkets simultaneously, handles Spanish characters/accents, partial matches, and common/brand names, and returns structured results (images, prices, links, etc.). It lacks details on rate limits, authentication needs, or error handling, but covers core functionality 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 well-structured and front-loaded with the core purpose, followed by details on functionality and results. It uses bullet points for clarity, but could be slightly more concise by integrating some points (e.g., combining search handling features into a single sentence). Overall, it avoids redundancy and each sentence adds value.

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 (3 parameters, no output schema, no annotations), the description is largely complete. It covers purpose, usage, behavioral traits, and result format. However, it lacks output schema details (e.g., structure of returned data) and does not mention potential limitations like API errors or pagination, leaving minor 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 schema description coverage is 100%, so the schema already documents all parameters (query, maxResults, sortBy) thoroughly. The description adds no additional parameter semantics beyond what the schema provides, such as examples or edge cases, meeting the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose with specific verbs ('search for products') and resources ('across all Argentina supermarkets'), distinguishing it from siblings like 'search_by_code' (which searches by code) and 'compare_prices' (which may compare specific products). It explicitly mentions searching by name or description and returning price comparisons.

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: for finding best deals and comparing prices across stores. However, it does not explicitly state when not to use it or name alternatives (e.g., 'search_by_code' for barcode searches or 'get_best_deals' for curated deals), leaving some ambiguity about sibling tool differentiation.

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 does well by mentioning the Firebase setup requirement and describing broadcast vs targeted delivery modes. However, it lacks details about rate limits, error conditions, authentication needs, or what happens when deviceToken is invalid - important for a notification 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 and appropriately sized. The first sentence states the core purpose, followed by a bulleted list of capabilities, and ends with an important prerequisite note. Every sentence adds value with no redundant information.

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

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

For a notification tool with 4 parameters, no annotations, and no output schema, the description is adequate but has gaps. It covers the main purpose and usage context well, but lacks information about return values, error handling, or detailed behavioral constraints that would be important for reliable tool 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 schema has 100% description coverage, so the baseline is 3. The description adds value by explaining the semantic meaning of parameters: deviceToken determines targeted vs broadcast delivery, and data can include product links/images. It also clarifies that title and message are required, though this is already in 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 with specific verbs ('send', 'broadcast') and resources ('push notification', 'device', 'subscribed devices'). It distinguishes this tool from siblings like 'subscribe_device' or 'set_price_alert' by focusing on notification delivery rather than subscription or alert creation.

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 about when to use this tool (for sending notifications with custom data about deals/updates) and mentions the Firebase Cloud Messaging prerequisite. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools.

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

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

With no annotations provided, the description carries full burden. It discloses key behavioral traits: the tool creates alerts that trigger automatically when prices drop below targets, monitors across supermarkets, and sends notifications. However, it lacks details on persistence (how long alerts last), error handling, authentication requirements (though userId is optional), or rate limits, which are important for a creation 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 clear sections (Features, Perfect for, Example) and front-loaded with the core purpose. However, some bullet points (e.g., 'Budget-conscious shopping') are slightly redundant with others, and the marketing tone ('Never missing a good deal') adds minor fluff that doesn't aid tool selection.

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 creation tool with no annotations and no output schema, the description is moderately complete. It covers the what and why but lacks details on behavioral constraints (e.g., limits on alerts per user), error cases, or response format. Given the complexity of setting up automated monitoring, more operational context would be helpful for an agent to use it correctly.

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

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

Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds minimal value beyond the schema—it mentions monitoring by 'name or barcode' and 'target price' but doesn't explain parameter interactions or provide additional context like format examples beyond the schema's descriptions. Baseline 3 is appropriate when schema does the heavy lifting.

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

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

The description clearly states the tool's purpose with a specific verb ('Set a personalized price alert') and resource ('for a product'). It distinguishes from siblings like 'get_my_alerts' (which retrieves alerts) and 'remove_price_alert' (which deletes alerts) by focusing on creation. The opening sentence directly answers 'what does this tool do?'

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 'Perfect for:' section provides clear context on when to use this tool (waiting for sales, tracking price drops, budget shopping). However, it doesn't explicitly state when NOT to use it or name specific alternatives like 'compare_prices' for immediate price checking or 'get_best_deals' for finding current discounts, leaving some ambiguity about tool 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 the full burden of behavioral disclosure. It clearly indicates this is a registration/mutation operation (implied by 'subscribe' and 'registers'), describes what happens after subscription (types of notifications received), and mentions the authentication requirement (Firebase token). However, it doesn't cover important behavioral aspects like whether the subscription is persistent, if there are rate limits, or what happens on duplicate subscriptions.

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 structured and front-loaded with the core purpose in the first sentence. Each subsequent sentence adds valuable information about what notifications will be received and the token requirement. There's zero wasted text, and the bulleted list efficiently communicates the notification types without unnecessary elaboration.

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

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

For a mutation tool with no annotations and no output schema, the description does a reasonable job covering the basic operation and requirements. However, it lacks information about the return value (success/failure indicators, subscription ID), error conditions, or persistence details that would be important for an agent to use this tool effectively in production scenarios.

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 100% description coverage for its single parameter, so the baseline is 3. The description adds meaningful context by explaining that the deviceToken parameter must be a 'valid Firebase Cloud Messaging device token' and connects it to the notification system registration, providing additional semantic understanding beyond the schema's technical specification.

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 ('Subscribe a device') and resource ('to receive push notifications about deals and price alerts'), distinguishing it from sibling tools like 'set_price_alert' or 'send_notification' which handle different notification-related functions. It explicitly defines the scope of notifications the device will receive.

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 (registering a device for notifications) and includes a prerequisite note about requiring a valid Firebase token. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools for similar notification-related tasks.

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