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

No annotations are provided, so the description carries full burden. It does not disclose side effects, auth requirements, or state changes beyond stating it adds to a real basket.

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-loaded with the action and a clear usage condition. No wasted words or unnecessary detail.

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

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

With 9 parameters, no output schema, and no annotations, the description is too minimal. It omits important context like prerequisites, error handling, and what happens to the basket after adding.

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 only 22%, and the tool description does not explain any parameters. It adds no value beyond the minimal schema, leaving most parameters ambiguous.

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?

Clearly states 'Add a product to the real Glovo basket' with specific verb and resource. Distinguishes from sibling tools like glovo_remove_from_basket and glovo_set_quantity.

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 instructs to call only when user explicitly asks for a real basket change, providing a clear usage condition. However, lacks guidance on when not to use it or comparisons to alternatives.

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 must cover behavioral traits. It mentions 'enrich a bounded recent subset' and 'explicit coverage,' hinting at limits and what is included, but does not specify whether the tool is read-only, if it modifies data, or any side effects. It adequately describes the process but lacks depth on safety or idempotence.

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 sentence that packs substantial information without unnecessary words. It is front-loaded with the main action. However, it could be slightly restructured for readability, but overall it is concise.

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 tool has no output schema, so the description should explain return values. It mentions calculating 'product frequency, cadence, customization, and visible-spend statistics,' giving an idea of the output, but not its structure or format. With 4 optional parameters, the description covers the process but lacks full completeness on output and prerequisites.

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 baseline is 3. The description adds contextual meaning like 'bounded recent subset' which relates to detail_limit, but the schema already explains each parameter's purpose and defaults. The description does not significantly enhance understanding 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 states a specific action: walking cursor-correct history, enriching a bounded recent subset, and calculating various statistics. It clearly distinguishes from sibling tools like glovo_get_purchase_history, glovo_get_order_items, and glovo_get_order_stats by offering an aggregated analysis rather than raw data retrieval.

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 when to use the tool (for aggregated statistics) but does not explicitly mention when not to use it or suggest alternatives. It could be improved by stating that for raw history or individual order details, other sibling tools should be used.

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?

The description indicates a read-only operation checking state, which is transparent. However, it does not explicitly state that it has no side effects or requires no permissions, which would be helpful.

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 the action and resource. No superfluous 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 simple status check tool with no parameters and no output schema, the description is adequate but lacks details about the return value format (e.g., boolean or object). Some ambiguity remains.

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?

There are no parameters, so the description does not need to add semantic information. The schema coverage is 100% trivially, and the description adds no redundant param info.

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

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

The description clearly states the verb 'Check' and the resources 'session availability' and 'access token validity'. It distinguishes itself from sibling tools like 'glovo_login' which creates a session.

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 verifying authentication status but does not explicitly state when to use it (e.g., before other operations) or mention alternatives. No when-not-to-use guidance.

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

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

No annotations provided, so description carries burden. Implies non-destructive read operation ('browse live stores'), but lacks details on authentication requirements, rate limits, or pagination behavior beyond parameter names. No mention of whether it returns full store list or paginated 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: first states main action and resource, second provides critical category_id details. No unnecessary words, front-loaded with purpose.

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

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

Given no output schema and no annotations, the description omits expected return format (e.g., list of stores with fields) and pagination details. Does not mention that a location must be configured. Adequate for a simple browse, but could be more thorough.

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% with descriptions for all parameters. Description adds value by enumerating specific category_id mappings (1,3,4) beyond the schema's 'Default 4 (groceries); use 1 for food.' This helps agent select correct category.

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?

Clearly states 'Browse live Glovo stores for the configured location' with specific verb and resource. Provides category_id mappings (1=restaurants, 4=groceries, 3=pharmacy/beauty) that distinguish it from sibling tools like glovo_search_store_items.

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 vs. siblings like glovo_search_store_items or glovo_get_store_order_options. Does not mention prerequisites such as setting a location first via glovo_set_location.

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 description carries full burden. It discloses read-only behavior and mentions authentication context ('authenticated Glovo basket'), but does not detail response format, error conditions, or side effects.

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, zero wasted words. The core action is front-loaded in the first sentence, and the conditional variation is efficiently stated in the second.

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 simple read tool with one optional parameter, the description is adequate but incomplete: it lacks details about the response (basket contents, status) and does not mention error conditions (e.g., authentication failure, missing basket).

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 optional store_id parameter is explained: if provided, it reads a different store's basket. Schema coverage is 0%, so description adds crucial meaning beyond type 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?

Description clearly states it reads the current Glovo basket, with a conditional variant for a store-specific basket. The verb 'read' and resource 'basket' are specific, and it distinguishes from mutation siblings like glovo_add_to_basket.

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?

Description implies use for reading basket state, but does not explicitly advise when to use this versus alternative tools such as glovo_add_to_basket or glovo_remove_from_basket. No usage exclusions or prerequisites are stated.

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 carries full burden. It clearly states it's read-only and does not mutate, but does not explain what the headers are or what the return format looks like.

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 concise sentences that directly state purpose and safety, with no filler.

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 0-parameter tool with no output schema, the description tells the purpose and safety but lacks any description of the return value or structure, leaving the agent uncertain about what to expect.

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, so schema coverage is 100%. Baseline 4 applies; description adds no parameter info because none exist.

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

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

Explicitly states the verb 'Read' and the resource 'current Glovo browsing location headers' and distinguishes from mutation tools by noting it does not mutate baskets.

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?

Provides no guidance on when to use this tool versus alternatives like other getters or location tools. The only hint is the non-mutating behavior, but no explicit when-to-use or when-not-to-use.

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?

The description indicates a read-only operation ('Read'), which is appropriate. With no annotations, the description alone discloses no mutation, but does not mention authentication requirements, rate limits, or behavior for invalid order IDs.

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, concise sentence with no superfluous words. It directly conveys the tool's function and is front-loaded.

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

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

Given the tool's simplicity (one parameter, no output schema), the description covers the essential purpose. However, it does not describe the format or structure of the returned items, which would aid the agent in handling the response.

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 covers the single parameter with 100% coverage. The description adds valuable context by specifying that the order_id comes from glovo_get_purchase_history, linking the tools and providing source guidance.

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

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

The description clearly states the action ('Read') and resource ('details/items for one past Glovo order'), making the purpose unambiguous. However, it does not differentiate from related tools like glovo_get_order_stats, which also concern order details.

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 such as glovo_get_purchase_history or glovo_get_basket. The description implies use for retrieving items of a specific past order, but does not advise on exclusions or 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 must fully disclose behavioral traits. It mentions cursor pagination and compact statistics but omits critical details such as the read-only nature, rate limits, handling of pagination responses, or what happens with large histories. This is insufficient for an agent to anticipate side effects or constraints.

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

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

The description is extremely concise at two sentences with no redundant information. The first sentence front-loads the core action and result, making it efficient for quick comprehension.

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 involves pagination and statistics, the description lacks output schema guidance, parameter explanations, and behavioral details. It does not specify the format or structure of the returned statistics, leaving the agent uncertain about the output. Without annotations or additional context, it is incomplete for safe and correct 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?

Schema coverage is 0% and the description does not explain the parameters 'max_pages' or 'page_delay_ms'. An agent cannot infer what values to use (e.g., page_delay_ms in milliseconds? how max_pages affects results?) from the description alone, leaving a critical gap.

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

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

The description 'Walk full order-history cursor pagination and return compact card-only statistics' clearly identifies the action (paginate and return statistics), the resource (order history), and the output type (compact card-only statistics). It distinguishes from siblings like glovo_get_order_items which provide detail enrichment.

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

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

The description explicitly states that 'Detail enrichment is intentionally separate,' guiding users to use other tools for detailed item information. However, it does not list alternative tool names or specify when not to use this tool beyond that hint.

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 present. The description only states the basic action without disclosing any behavioral traits such as output format, authentication requirements, or side effects.

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 very concise but lacks necessary structure for a tool with multiple parameters; it under-specifies important 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?

With no output schema and no annotations, the description fails to provide sufficient context for an agent to correctly use the tool, especially regarding parameter usage and expected return data.

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%, and the description adds no information about the six parameters, leaving their purpose unclear beyond what the schema 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?

Description clearly states the action ('Get product details') and resource ('from a store'), and distinguishes from sibling tools like glovo_search_store_items by specifying the input source.

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?

Provides clear context for use: product ids from glovo_search_store_items. No explicit when-not-to-use, but the prerequisite is well indicated.

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?

Discloses pagination behavior and read-only nature, but with no annotations, the description carries full burden. Lacks details on authentication requirements, rate limits, or error handling.

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 concise sentences: first defines purpose, second explains pagination. No redundant information; every sentence serves a clear function.

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?

Adequately covers pagination mechanics, which is the main complexity. However, with no output schema and no annotations, the description could mention return format or prerequisites like authentication. Still, it is largely complete for a read-only tool with two well-documented params.

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 has 100% coverage with descriptions. The description adds the usage pattern 'start with offset 0, then pass the returned next_offset', but this is mostly a clarification of existing schema info. No significant additional meaning beyond 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?

Clearly states 'Read authenticated Glovo order history' – a specific verb (Read) and resource (order history). Distinguishes from siblings like glovo_get_order_items and glovo_get_order_stats.

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?

Explains cursor-based pagination with offset and next_offset, providing clear usage context. However, no explicit guidance on when to use this tool vs. siblings or 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?

Given no annotations, description adequately discloses read-only nature and lack of side effects ('does not change location headers or baskets'). Could mention authentication requirements or rate limits, but still clear.

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 redundant words, front-loaded with main action first. Highly 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?

Covers core behavior and read-only guarantee. Lacks output structure description, but tool is simple and no output schema exists. Adequate for its purpose.

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?

Parameter `match_text` is fully described in the schema (100% coverage). Description adds 'identify the current saved-location match' but does not significantly augment schema details. Baseline 3 is appropriate.

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 clearly states the verb 'Read' and resource 'authenticated saved Glovo delivery locations', adding nuance about identifying matches. It distinguishes from sibling tools like glovo_set_location by emphasizing read-only behavior and no side effects.

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?

Implicitly indicates usage for reading saved locations or finding a match, and states it is read-only. However, it does not explicitly compare to siblings like glovo_get_location, which might also read location data.

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

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

No annotations provided; description states it returns a playbook and safety rules. Adequately implies no side effects, but lacks details on return format or whether it requires auth. Acceptable for a no-parameter 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?

Single sentence, front-loaded with purpose, then usage instruction. Every word earns its place with zero 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?

Despite no output schema, the description fully captures what the tool does and when to use it. No further details are necessary given the tool's simplicity.

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 exist, so schema coverage is complete. Baseline of 4 applies as no param information is needed.

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?

Clearly states it returns 'Glovo shopping playbook and safety rules' and specifies to call before modifying basket. Distinct from sibling tools that perform actions like add_to_basket or remove_from_basket.

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 instructs 'Call this before changing a basket,' providing clear when-to-use context. Does not cover when not to use, but the guidance is sufficient for this simple read-only tool.

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

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

No annotations are provided, so the description carries the full burden. It clearly labels the operation as read-only by using 'Read' and stating 'No checkout or order placement'. It lists the data returned but does not disclose permissions, rate limits, or side effects, though for a read-only tool this is minimally acceptable.

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 two sentences long, front-loads the key purpose, and contains no redundant words. Every sentence 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?

With four parameters, no output schema, and no annotations, the description provides a high-level understanding but lacks guidance on how to use specific parameters (e.g., translation language, similar_limit). It is minimally complete for an agent to infer behavior but leaves gaps.

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

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

Schema description coverage is 50% (only 'translation' and 'similar_limit' have schema descriptions). The tool description does not add any parameter-specific information beyond the schema, failing to compensate for the missing schema descriptions of 'store_id' and 'store_address_id'.

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

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

The description clearly states the verb 'Read' and the resource 'store order options', listing specific elements like delivery minimums, surcharges, restrictions, public store info, and similar stores. It also distinguishes itself from siblings by noting it is a pre-basket read operation, not checkout or order placement.

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

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

The description explicitly states 'before preparing a basket' (when to use) and 'No checkout or order placement' (when not to use). However, it does not name specific alternative tools for comparison, but the context is clear enough for an agent to decide.

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?

The description explicitly states 'Never changes the basket' and 'read-only', which are key behavioral traits. It also mentions re-fetching current products and optional Google Maps evidence. With no annotations provided, this description covers essential behavioral aspects but lacks details on authentication 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 two sentences, front-loaded with the core purpose, and every word adds value. No redundancy or wasted text.

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?

With 11 parameters and no output schema, the description covers the main behavior but does not explain the structure of the returned choices (e.g., whether they include venue names, product details, pricing). This omission means the agent lacks full context on what the tool returns.

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%, so baseline is 3. The description adds little beyond the schema; it mentions 'repeat, explore, or balanced food intent' which maps to the 'mode' parameter, but does not elaborate on other parameters. The schema itself provides adequate descriptions.

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 converts structured food intent (repeat/explore/balanced) into 3-5 read-only live choices, using venue history and re-fetching products. It distinguishes itself from siblings by focusing on personalized suggestions based on intent, not browsing or analysis.

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

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

The description implies usage when a food intent is known (repeat/explore/balanced), but it does not explicitly compare to sibling tools like glovo_browse_stores, glovo_search_store_items, or glovo_analyze_order_history, leaving the agent without clear guidance on when to choose this tool over alternatives.

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 that Chrome is opened and a local session is saved, but lacks details on side effects (e.g., user interaction required, browser state modification, timeout behavior, or re-login implications).

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, front-loaded sentence that efficiently conveys the action and purpose. No redundant or extraneous content.

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 simple input schema (one optional integer) and no output schema, the description adequately explains the tool's role for subsequent tools. However, it could be enhanced by noting that it requires a browser environment and may involve manual login steps.

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%, with a clear description for the single parameter (timeout_ms). The tool description adds no parameter information, but baseline is 3 when schema coverage is high. Thus score is adequate.

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

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

The description clearly states the action ('Open Chrome for Glovo sign-in') and the purpose ('save the local session for order history and basket tools'). It distinguishes the tool from siblings by indicating it is a prerequisite for other tools like basket and history.

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 as the first step for other tools by mentioning 'save the local session for order history and basket tools.' However, it does not explicitly state when not to use it or offer alternatives, though sibling names like glovo_auth_status suggest a complementary 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 the full burden. It clearly states the tool is read-only and that users should inspect product options and obtain approval before using basket tools. This disclosure of non-destructive behavior is valuable, though more detail on return format or auth needs would strengthen it.

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 two sentences with no filler. The first sentence conveys the core action, and the second provides usage context. Every word earns its place.

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

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

Given the tool has no output schema and three parameters, the description is minimal. It lacks details on what the output looks like or how to interpret results (e.g., which products are unavailable). For a reorder planning tool, more context on the resolution process would improve completeness.

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

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

Schema coverage is 100%, so baseline is 3. The description adds no parameter-level information beyond the schema; it does not explain what max_searches or candidates_per_line control in relation to the planning process. This is adequate but not enhanced.

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 resolves past order lines against current store results for planning a repeat order. This distinguishes it from general basket tools and suggests a planning role, though the difference from glovo_preview_reorder is not explicit.

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 this tool is a read-only planning step before using basket tools, but does not explicitly state when to use it over similar tools like glovo_preview_reorder or glovo_add_to_basket. More concrete when-to-use and when-not-to-use guidance would help.

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?

Explicitly states no mutation ('never mutates the basket or places an order'), which is critical for safe usage. With no annotations, description carries full burden and does 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?

Two sentences, no fluff, front-loaded with key purpose. Efficient and clear.

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

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

Lacks return format details (e.g., boolean or status), but for a read-only preview tool, the description provides sufficient context for safe usage despite no 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 for order_id already indicates source (glovo_get_purchase_history). Description adds 'past order' context but limited extra value; schema coverage is 100%.

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?

Clearly states verb ('Read'), resource ('one past order'), and outcome ('report whether it can be safely rebuilt into a basket'). Distinguishes from mutation tools by emphasizing it never mutates.

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?

Implicitly suggests when to use (to check rebuild feasibility) but lacks explicit exclusions or references to sibling tools like glovo_add_to_basket for actual reordering.

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 states the action but discloses no side effects, prerequisites, or response behavior. The agent is left uninformed about error states or confirmation requirements.

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

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

The description consists of two short, direct sentences with no redundancy. However, it could be more structured by including key parameter hints without adding much 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?

For a tool with 4 parameters, no schema coverage, and no output schema, the description fails to provide essential invocation context. The agent cannot reliably construct correct calls without guessing parameter roles.

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%, yet the description provides zero information about the four parameters (store_id, product_id, store_product_id, basket_product_id). The agent cannot determine which parameter distinguishes the product to remove or that store_id is required.

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 'Remove one product from the real Glovo basket,' which clearly identifies the action (remove) and the resource (product from basket). This purpose is distinct from sibling tools like glovo_add_to_basket and glovo_get_basket.

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 instruction 'Do not call unless explicitly requested' provides a clear usage constraint, implying the tool should only be used when the user directly asks to remove a product. However, no alternatives or when-not-to-use scenarios 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?

Discloses that it returns only place id, provider, title, and subtitle – a key behavioral detail beyond the schema. No annotations provided, so description carries burden. Does not mention pagination, error behavior, or auth requirements, but acceptable for a simple search 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?

Single sentence with no wasted words. Includes both action and output description. Well-structured for readability.

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?

Adequately covers purpose and output for a simple search tool with 2 parameters and no output schema. Could mention that it searches only public locations, but not necessary given the title.

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?

Input schema has 100% description coverage for both parameters (query and limit). Description adds no additional meaning beyond schema – baseline 3 is appropriate.

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?

Clearly states 'search public Glovo delivery locations by text' – specific verb and resource. Distinguishes from sibling tools like glovo_get_location (single location) and glovo_browse_stores (stores). However, does not explicitly contrast with siblings.

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

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

No guidance on when to use this tool vs alternatives (e.g., glovo_get_location for a specific location, glovo_browse_stores for stores). Implied usage from name and description, but lacks explicit direction.

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 exist, so the description carries full burden. It fails to disclose behavioral traits such as whether the operation is read-only, authentication requirements, or pagination behavior. Only states 'Search' without additional 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?

Two sentences: first states purpose, second gives prerequisite. No fluff, front-loaded, every sentence 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 no output schema, the description should explain return format, pagination, or error handling. It does not, leaving the agent uninformed about the response structure.

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 50% (limit and query described). The description adds valuable context for store_id and store_address_id by referencing sibling tools, and provides example search terms for query, compensating for missing schema descriptions.

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 products/items inside a specific Glovo store. It names the specific verb and resource, and mentions using ids from sibling tools, which helps differentiate from tools like glovo_browse_stores.

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

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

It advises using ids from glovo_browse_stores or glovo_get_store, providing prerequisite context. However, it does not explicitly state when to use this tool versus alternatives like glovo_get_store_menu or glovo_get_product.

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 must disclose behavioral traits. It mentions checking serviceability and persisting valid headers, but it does not describe error handling (e.g., when serviceability fails), auth requirements, or side effects like session changes.

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?

A single, well-structured sentence that packs all key information without verbosity. 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?

The description explains the outcome but lacks details about the return value (no output schema). It does not cover the complete context for a tool that performs validation and persistence, leaving gaps about possible errors or success signals.

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% coverage with descriptions for both parameters. The description adds little beyond that, only hinting that these come from glovo_search_locations. Since schema is already clear, baseline 3 is appropriate.

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 specific purpose: resolving a public location suggestion, checking guest delivery serviceability, and persisting valid browsing location headers. It distinguishes itself from sibling tools like glovo_search_locations (which only suggests) and glovo_set_location (which may not include validation).

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 after glovo_search_locations by referencing its outputs, and it clarifies the validation and persistence steps. However, it does not explicitly state when not to use it or mention alternatives like glovo_set_location for setting a location without validation.

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 explicitly states that setting location does not clear baskets but warns that changing stores may make a basket incompatible, which is a key behavioral trait.

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-loaded with the main purpose, and the second sentence adds a behavioral note. No wasted words.

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

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

Given no annotations, no output schema, and five undocumented parameters, the description is not fully complete. It covers the core behavior and side effect but misses parameter details and return value description.

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% and the description adds no information about the five parameters. Although parameter names are self-explanatory, the description should compensate for the lack of schema descriptions, but it does not.

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 sets location headers, and distinguishes from siblings like glovo_select_location and glovo_search_locations by focusing on direct header setting.

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 mentions a caveat about basket incompatibility when changing stores, but does not provide explicit guidance on when to use this tool versus alternative location-related tools (e.g., glovo_select_location or glovo_search_locations).

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; description carries full burden. It discloses that the tool sets exact quantity and that 0 removes the product. It does not mention mutation of the live basket or other side effects, but baseline behavior is covered.

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

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

Two sentences that efficiently convey purpose, a special case (quantity 0), and a usage warning. 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?

Despite 5 parameters and no output schema, the description omits parameter details and return value. The tool's complexity demands more context for effective use, especially given zero schema coverage.

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

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

Schema description coverage is 0%, and the description provides no explanation of parameters like store_id, product_id, etc. The agent must rely solely on parameter names, which is insufficient for a 5-parameter tool.

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

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

The description clearly states the verb 'set' and the resource 'exact product quantity in the real Glovo basket,' distinguishing it from siblings like add or remove. It also specifies that quantity 0 removes the item, which is a key behavioral detail.

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 includes 'Do not call unless explicitly requested,' giving a clear usage restriction. However, it does not compare with sibling tools like add_to_basket or remove_from_basket to guide when to use alternatives.

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