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

With no annotations, the description must disclose behavior. It reveals that missing required fields cause 422 errors and suggests recovery. However, it does not mention that this is a mutation (adds to cart) or any authentication/rate-limit details.

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

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

Two sentences, front-loaded with purpose, no extraneous text. Every phrase contributes guidance.

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 add-to-cart tool with no output schema, the description covers the key prerequisites and error handling. It could mention success indication but is generally complete.

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

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

Schema coverage is 80%; the description adds value by specifying the mapping from market_search output fields (especially 'store' from 'store_key'), which goes beyond the schema descriptions. It also implicitly covers the required parameters.

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

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

The description clearly states the action ('Add to cart') and the domain ('[Shop]'), with specific resource identification. It explicitly lists the four required fields from market_search, distinguishing it from siblings like market_cart_update and market_checkout.

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 explicit instructions to copy all four fields from market_search and warns about 422 errors for missing fields, advising to re-run market_search if needed. Lacks explicit when-not-to-use guidance but gives clear usage 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?

No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention data freshness, update frequency, side effects, or limitations. The term 'One-call' implies simplicity but lacks detail on underlying methodology or dependencies.

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 and relatively concise, though the first sentence uses bracketed '[Intel]' and jargon that may not be universally clear. It front-loads the key purpose but could be more structured or accessible.

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

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

Given the tool's complexity (a composite of multiple indicators) and no output schema, the description is too minimal. It does not explain what the output contains (e.g., numeric index, categories, breakdowns) or how to interpret the results. Additional context is needed for an 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 coverage is 67%. The description adds no additional meaning beyond the schema; it does not explain how country, line, or days affect the composite. The schema provides minimal descriptions (e.g., country lists values but no semantics, line has no description, days has only 'Analysis window'). The tool's purpose description does not compensate for missing parameter context.

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

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

The description clearly states the tool provides a cost-of-living composite for LATAM, mentioning specific components like canasta pressure, wage ratio, macro gap, and regulatory headlines. The name and description together convey the purpose of assessing market affordability, distinguishing it from sibling tools like market_inflation or market_scores.

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. The description does not mention any exclusion criteria or comparative advantages over other market tools from the sibling list. The agent would need to infer usage from the purpose alone.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as whether the tool modifies state (e.g., adds to cart), returns results, or requires authentication. For a tool with no annotations, this is insufficient.

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, one sentence with examples. No filler or repetition.

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 tool with one parameter and no output schema, the description provides purpose and examples but lacks behavioral context. It is adequate but not 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?

The single parameter 'prompt' is described in the schema as 'Natural-language instruction', and the description adds examples. Since schema coverage is 100%, the baseline is 3, and the description adds minimal extra meaning.

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 identifies the tool as natural-language shopping, with specific examples ('buy milk', 'repeat last purchase', 'compare rice') that differentiate it from siblings like market_search or market_compare.

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

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

The description gives examples of use but does not explicitly state when to use this tool versus alternatives or when not to use it. It provides minimal guidance on 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, the description must disclose behavior but only mentions a lookup. It does not state that the operation is read-only, what happens on invalid barcodes, or any expected return format. Minimal behavioral insight.

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 that immediately conveys the tool's purpose. It is front-loaded and efficient, though could be more detailed without sacrificing brevity.

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, the description should ideally mention return values. It does not, but for a simple lookup, the basic purpose is clear. However, completeness is limited compared to the richness of sibling tools.

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

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

The schema already describes the 'code' parameter as an EAN/UPC barcode (100% coverage). The description adds no additional semantics beyond what is in the schema, so baseline score of 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 looks up a product by barcode, using specific verb 'look up' and specific resource 'product by EAN/UPC barcode'. This distinguishes it from sibling tools like market_search (generic search) and market_add (adding 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?

The description implies usage when a barcode is available, but lacks explicit guidance on when not to use it or comparison to alternatives like market_search for product name lookups. No usage context or exclusions 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?

No annotations are provided, so the description carries the full burden. It describes the tool as comparing and returning results, implying a read-only operation, but does not explicitly state that no data is mutated, nor does it mention any prerequisites, rate limits, or side effects. The description adds some behavioral context (LATAM differentiator) but lacks sufficient 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?

Description is concise, with no wasted sentences. It front-loads the main purpose and includes key differentiators. However, it could be more structured (e.g., bullet points for parameters or usage steps), but remains efficient.

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

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

Given no output schema and no annotations, the description provides adequate context for a comparison tool. It explains what it does, how to use it (pass items), and adds regional context. However, it lacks details about return format or behavior when no matches found, which would be helpful for complete understanding.

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%, with each parameter having a description. The tool description adds some context for the 'items' parameter ('Pass items with name and qty') but does not add significant meaning beyond what the schema already provides. Baseline 3 is appropriate as the 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?

Description clearly states the verb 'compare' and resource 'total basket cost across retailers'. It specifies that items are passed with name and qty, and returns per-store totals and cheapest retailer. The LATAM differentiator and mention of 41 verified retailers across 8 countries further clarifies scope and distinguishes it from sibling tools.

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

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

Description implies usage by stating 'Pass items with name and qty' and optional filters, but does not explicitly state when to use this tool versus alternatives like market_compare or market_search. No exclusions or when-not guidance is provided, so usage context is implied but not explicit.

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 disclose behavior. It states 'View' implying idempotency, but lacks details on side effects, authentication, or rate limits. Adequate but minimal.

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 '[Shop]', no wasted words. Perfectly concise for a zero-parameter tool.

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 enumerates key return fields (products, quantities, prices, total). Could mention structure or example, but sufficient for a simple view operation.

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

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

The input schema has no parameters, so no additional meaning needed. Baseline is 4 as per guidelines. Description adds context by listing output fields.

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

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

The description clearly states the tool retrieves the current cart with specific details (products, quantities, prices, total). It distinguishes from siblings like market_cart_update and market_checkout by specifying viewing only.

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 a read-only view but does not explicitly state when to use vs alternatives such as market_cart_update or market_checkout. No exclusions or context 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?

No annotations are provided, so the description carries full burden. It discloses the removal behavior via quantity=0 but does not mention side effects, error conditions, authorization requirements, or rate limits. For a mutation tool, more behavioral context is needed.

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: two sentences that directly convey the purpose, a key usage note, and a versioning hint. Every word earns its place with no redundancy.

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

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

Given the low complexity (2 simple params, no output schema, no annotations), the description covers the core operation. However, it lacks information about what happens on success (e.g., return value), error conditions (e.g., invalid product_id), or prerequisites (e.g., product must be in cart). For a complete understanding, an agent would need to infer or test.

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% but the description adds significant value: the '[Shop]' prefix provides domain context, the note about quantity=0 clarifies the removal functionality, and the replacement note gives historical context. This goes well 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?

Clearly states the action 'change item quantity' and the resource 'cart'. The description also specifies the special case of quantity=0 for removal and mentions it replaces a previous sibling (market_cart_remove), effectively distinguishing it from related tools even though market_cart_remove is not in the sibling list.

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 explicit guidance on using quantity=0 to remove items, which is a key use case. It also references the replacement of market_cart_remove, offering context. However, it does not explicitly state when not to use the tool or provide alternatives beyond the removed tool, though the sibling list is extensive.

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, description carries full burden. It reveals that the tool creates an internal order (not a real checkout) and requires Pro tier for live charge, but does not disclose side effects like cart modification or idempotency.

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

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

Description is concise (3 sentences) and front-loaded with purpose. Could be more structured with bullet points but no 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?

For a simple one-parameter tool with no output schema, description covers main purpose, internal order nature, Pro requirement, and payment methods. Missing info on success/failure indicators and whether cart is cleared.

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 description adds no new semantic value beyond restating payment methods. Baseline 3 applies.

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 tool pays for the cart via CLI Market, specifies internal order creation (not retailer checkout), and lists supported payment methods. It distinguishes from sibling tools like market_cart and market_orders.

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 mentions Pro tier requirement and references /v1/capabilities, but does not explicitly state when to use this tool over alternatives like market_cart or market_orders. Lacks '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 the description must convey behavior. It mentions timeout avoidance with country/store, but does not disclose return format, pagination, error handling, or data freshness. Adequate but not thorough.

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 waste. First sentence gives purpose and constraint (one query, side-by-side). Second sentence gives usage guidance and a practical hint. Front-loaded and 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?

With 6 parameters and no output schema, more detail could be helpful. While schema covers parameters, the description omits what 'side-by-side' results look like (e.g., list, table) and doesn't explain line or TCO. Adequate for a basic tool but could be richer.

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 83%, so most parameters are described. The description adds context beyond schema, e.g., 'Set country (e.g. PE) or store to avoid timeouts,' which explains the performance implication. Provides examples and usage tips.

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 'Compare prices for one query across retailers side-by-side,' which is a specific verb+resource. It distinguishes from siblings like market_search and market_discover.

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 says 'Use when the user asks for cheapest option or cross-store comparison,' providing clear when-to-use guidance. Also hints at setting country or store to avoid timeouts, though no explicit when-not or 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 provided, so description carries the full burden. It does not mention any safety traits (read-only, destructive) or side effects. Only indicates what data is returned, but lacks behavioral 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?

Two concise sentences, front-loaded with '[Shop]' label, minimal waste. Every 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?

Adequate for a discovery tool with two optional filters. No output schema, but description mentions three data dimensions. Lacks details on pagination or format, but sufficient for typical use.

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

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

Schema coverage is 100% with well-described optional parameters. Description adds context about 41 retailers across 8 countries but does not enhance param understanding 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?

Description clearly states the tool covers retail coverage in one call, listing business lines, retailers, and countries. It explicitly replaces three sibling tools, distinguishing its purpose.

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

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

Explicitly states it replaces market_lines, market_stores, and market_countries, guiding when to use this tool instead. No when-not guidance, but the replacement hint is strong.

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 only states the export action and tier requirement, but does not disclose side effects, how data is returned, or any destructive potential. Minimal 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 very short (one sentence plus a requirement), which is concise but at the cost of missing critical details like parameter explanations and usage context. It is front-loaded with '[Intel]' tag, but overall under-specified for its complexity.

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

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

Given 4 parameters with no schema descriptions, no output schema, and no annotations, the description fails to provide sufficient context. It does not explain what 'data moat' is, what each parameter does, or what the output looks like. Highly incomplete.

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

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

Schema description coverage is 0%, and the description adds no information about the four parameters (country, line, format, limit). It mentions CSV/JSON formats but does not link them to the format parameter or explain other params. Parameter semantics are completely missing.

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 'Export data moat as CSV or JSON', which clearly indicates the tool's action (export) and output formats. It distinguishes from sibling tools like market_search by focusing on export functionality, though 'data moat' is somewhat vague. Overall, purpose is clear.

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 only mentions a tier requirement ('Requires starter tier or above'), but gives no guidance on when to use this tool versus alternatives like market_intel_brief or market_stats. No when-to-use or when-not-to-use context is 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?

No annotations are provided, so the description must carry the full burden. It discloses the actions (list, add, remove) but does not explain side effects, authentication needs, or error behavior. The behavioral transparency is minimal.

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 with clear front-loading. It is concise and to the point, though it could be slightly expanded for completeness without losing brevity.

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

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

Given no output schema, no annotations, and low parameter coverage, the description is insufficient. It lacks information on return values, pagination, error handling, and how this tool fits into the broader workflow among 32 sibling tools.

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

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

Schema description coverage is only 25% (only 'action' has a description). The description adds 'Omit action for list' but does not explain the roles of product_id, name, or store, leaving their semantics unclear for add/remove operations.

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 'Manage favorite products: list, add, or remove,' clearly specifying the verb and resource. While it distinguishes from siblings by focusing on favorites, it could better contrast with similar tools like market_cart or market_substitutes.

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 guideline 'Omit action for list' provides a specific usage hint, but it lacks guidance on when to use this tool versus alternatives (e.g., market_cart for cart management) and does not mention prerequisites or exclusions.

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

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

No annotations are provided, so the description must fully disclose behavior. It states the profile includes budget, restrictions, etc., but does not mention whether authentication is required, if it is read-only, or any side effects. The lack of output schema further limits transparency.

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

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

The description is a single, efficient sentence that conveys the tool's purpose without any redundant information. Every word 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 zero parameters and no output schema, the description adequately covers the tool's return content (budget, restrictions, staple list, default stores). The '[Account]' prefix implies the tool operates on the current account. It is complete enough for a simple retrieval tool.

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

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

There are zero parameters, so the description does not need to add parameter information. According to guidelines, 0 parameters set a baseline of 4, 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 that the tool retrieves a household profile including specific elements like budget, restrictions, staple list, and default stores. The name 'market_household_get' reinforces the retrieval action, and the sibling tool 'market_household_update' provides contrast. However, the description could be more explicit about the verb 'get' or 'retrieve'.

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

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

The description does not provide any guidance on when to use this tool versus alternatives. No explicit context, prerequisites, or exclusions are mentioned. The agent must infer usage from the tool name and sibling 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?

No annotations are provided, so the description must disclose behavioral traits. It does not mention idempotency, destructive potential, permissions, or what happens on conflict. The phrase 'Create or update' implies mutation but lacks detail.

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

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

The description is a single, efficient sentence that conveys the essential action and scope. However, it omits important details that could fit within a concise format.

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 2 parameters (one nested object) and no output schema, the description lacks information about return values, error cases, or side effects. It is incomplete for full agent understanding.

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 baseline 3. The description adds context by naming specific fields (budget, restrictions, staples) within the payload, but does not detail the nested schema structure further.

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 (Create or update) and resource (household profile), listing key fields (budget, restrictions, staples). It distinguishes from sibling market_household_get, which is a read operation.

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 like market_household_get or other account tools. The '[Account]' prefix hints at scope but does not provide decision criteria.

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

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

With no annotations, the description carries full responsibility. It mentions '[Intel]' and 'data moat' but does not disclose behavioral traits like data freshness, permissions, or whether the tool is read-only or mutating.

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, front-loaded with '[Intel]' for context. Very concise with no unnecessary 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?

Adequate for a simple data retrieval tool with three optional parameters. However, it lacks details about output format or computation method, which would be helpful given 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 coverage is 100%, so the schema already documents each parameter. The description adds the context that both country and line are filters, but does not provide additional syntactic or formatting details beyond the schema.

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

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

The description clearly states it provides 'price deltas and average inflation' for shelf inflation, identifying the specific data output. However, it does not differentiate from sibling tools like market_inflation_report, which may have overlapping functionality.

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

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

No guidance on when to use this tool versus alternatives. It only mentions filtering by country or line but lacks context on prerequisites or exclusions.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the output (pressure level) but does not mention whether it's read-only, authentication requirements, rate limits, or if any data is modified. Given it's a report, likely safe, but not confirmed.

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

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

The description is concise, front-loaded with a tag, and fits in two sentences. It conveys essential information without waste, though the rhetorical question is slightly redundant.

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 optional parameters, the description explains return values but omits default behavior when no parameters are provided. It references two data sources without detailing their interaction, leaving some gaps for a report tool.

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

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

Schema coverage is 100%, so the schema already documents all three parameters. The tool description adds 'internal shelf inflation and macro CPI gap' as background context but does not elaborate on how parameters affect results beyond the schema descriptions. 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 returns a pressure level (stable/rising/rising_fast/falling/above_official) from internal shelf inflation and macro CPI gap, distinguishing it from sibling 'market_inflation' which likely provides raw data. The verb 'Returns' and resource 'pressure level' are specific.

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 begins with '[Intel]' hinting at business intelligence use, but does not explicitly state when to use versus alternatives like 'market_inflation' or 'market_intel_brief'. No when-not-to-use guidance is given.

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 the content scope (shelf signals, macro gap, etc.) but does not disclose behavioral traits such as whether it is read-only, authentication needs, rate limits, or side effects. Safety and idempotency are unaddressed.

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

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

The description is concise, front-loaded with a tag, and efficiently communicates purpose and replacement role without unnecessary 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?

With no output schema, the description lists what the narrative includes (shelf signals, macro gap, etc.) but does not describe the output format or structure. Given the tool's complexity and lack of annotations, more detail on return values 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 each parameter is already described in the input schema. The tool description does not add additional meaning beyond the schema descriptions, maintaining the baseline of 3.

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 provides an intelligence narrative covering shelf signals, macro gap vs CPI, composite scores, and moat confidence. Distinguishes from siblings by explicitly saying it replaces indicators, analytics, and enrichment reads, which are likely separate tools.

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

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

Indicates it is a one-call alternative to separate indicator, analytics, and enrichment tools, providing context for when to use it. However, it does not explicitly specify exclusions 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?

Discloses return values (access + refresh tokens), token lifetimes (90d, 365d), local persistence, and auto-refresh behavior on 401. Completely transparent for a login tool with no annotations.

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, all relevant information succinctly presented. No wasted words; every 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?

For a login tool with 2 parameters and no output schema or annotations, the description covers purpose, prerequisites, return behavior, token lifetimes, persistence, and error handling. Fully complete.

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

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

Schema coverage is 0% and description does not explain parameters beyond their names. While 'username' and 'password' are self-explanatory, the tool has 2 parameters and no additional constraints are mentioned (e.g., required vs optional). 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 it authenticates in CLI Market and is a prerequisite for cart, checkout, or orders. The verb 'authenticate' and resource 'CLI Market' are specific, and it distinguishes from sibling tools by its role as a gateway.

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 says 'Call before cart, checkout, or orders.' and describes when to re-login vs. rely on auto-refresh after a 401. Provides clear context for when to use this tool over others.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It mentions the tool 'optimizes' and 'replaces' workflows but does not state if it performs mutations, requires authentication, has rate limits, or what side effects occur. The lack of behavioral details is a significant gap.

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

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

The description is two sentences, front-loaded with the core value proposition 'one-call purchase optimization.' No redundant words; every 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?

Despite 4 parameters, nested objects, and no output schema, the description is very brief. It does not explain return values, error conditions, or parameter usage beyond the high-level purpose. For a tool with this complexity, more detail is needed.

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 50% (items and constraints have descriptions, country and include_intel do not). The tool description adds no parameter-specific explanations, relying entirely on the schema. Given the incomplete schema coverage, the description should have compensated but did 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 it performs 'one-call purchase optimization' with specific capabilities: basket compare, TCO, substitutes, intel, and action links. It distinguishes from sibling tools by replacing a multi-step workflow (search → compare → intel), making its purpose unique and well-defined.

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

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

The description indicates the tool is for consolidating fragmented steps (search, compare, intel) into one call, providing clear context. However, it does not explicitly list when not to use it or mention alternatives, though the sibling tools imply alternatives for individual steps.

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 'repeat the last order' but fails to clarify if this action is a purchase or a preview, nor does it mention authentication needs, side effects, or whether the operation is read-only or destructive.

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 concise sentences. The first sets context and purpose, the second gives a specific usage instruction. No unnecessary words, perfectly 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 has a mutating operation (reorder), the description is incomplete; it fails to explain what 'repeat the last order' entails (e.g., immediate purchase, addition to cart). No output schema means the agent cannot know what to expect. The description leaves critical 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 coverage is 100% and the description essentially repeats the schema description for the single parameter. It adds no new meaning beyond what is already in the schema, so a baseline score of 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 it is for 'Order history' and includes the reorder functionality, distinguishing it from other shop tools like market_cart or market_search. However, it lacks an explicit verb like 'view' or 'list', which would make it more precise.

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

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

The description provides no guidance on when to use this tool versus the many sibling tools. It only gives a conditional for the parameter but does not help the agent choose between market_orders and alternatives like market_cart or market_search.

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

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

With no annotations, the description carries full burden. It implies a read operation but does not explicitly state safety (e.g., read-only), authentication needs, or data freshness. It also does not disclose if the output is real-time or cached.

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 conveying essential information without waste. However, it could be slightly improved by starting with a verb (e.g., 'Get') for clarity.

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 parameters and no output schema, the description is the sole source of information. It covers key outputs but omits details like return format (list vs. object) and whether there are additional preference fields. More completeness would help the agent.

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

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

There are no parameters, so the schema provides no information. The description adds meaning by specifying the output content (favorite stores, total spent), which is valuable beyond the empty schema.

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

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

The description clearly states it returns user preferences (favorite stores, total spent) derived from purchase history. While it lacks an explicit verb like 'retrieve', the meaning is evident and distinguishes it from siblings like market_favorites (likely item-level) and market_scores (likely scoring).

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

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

No guidance is provided on when to use this tool versus alternatives such as market_favorites or market_scores. The description gives no context about appropriate usage scenarios or exclusions.

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

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

No annotations are provided, so the description must disclose behavioral traits. It implies both querying and configuring (mutation) but doesn't specify auth needs, side effects, or whether notifications are persistent. Absence of annotation burden is not carried.

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 is concise and front-loaded with '[Account]', but lacks structure. It could be split for clarity without adding 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 output schema, and no annotations, the description is too brief. It fails to explain what the return data looks like, how alerts are configured, or how it relates to sibling tools like market_subscription.

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 low (25%). The description adds some context for 'product' and the overall purpose, but store, threshold_pct, and limit are not elaborated beyond defaults and type. Meaning is insufficiently conveyed.

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 it handles querying drops and configuring threshold notifications for a product, which is specific. However, 'query drops' is somewhat vague, and it doesn't fully distinguish from siblings like market_price_risk or market_subscription.

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. The '[Account]' prefix implies it's account-specific, but no explicit context or exclusions are given.

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

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

No annotations are provided, so the description carries full burden. It only mentions the output (risk level and signals) but does not disclose behavioral traits such as read-only nature, authentication requirements, rate limits, or any side effects. Minimal disclosure.

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

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

The description is a single, well-structured sentence that front-loads the purpose and concisely details the output. No unnecessary 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?

No output schema exists, so the description should compensate. It explains the risk level and signals but lacks specifics on output format, whether results are per category or aggregated, and the meaning of the supporting signals. Decent but incomplete.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds context about the tool's output but does not elaborate on individual parameters beyond what the schema provides. Adequate but no extra meaning for parameters.

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

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

The description clearly states the tool provides price risk intelligence, returning a risk level (low/moderate/high) with supporting signals. It uses specific verbs and resources, and the purpose is distinct from siblings like market_price_alerts or market_trending.

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

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

The description implies use when seeking category volatility, but does not explicitly state when to use this tool versus alternatives or provide exclusions. No guidance on 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?

With no annotations, the description must carry the full behavioral burden. It mentions the input data sources (basket stress, search momentum, staple prices) and the output signal types, but does not disclose whether the tool is read-only, requires authentication, has rate limits, or any 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 a single well-structured sentence that front-loads the tool category '[Intel]' and key information. Every word serves a purpose, with no redundancy.

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

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

Given the simple two-parameter input and scalar output (one of three values), the description covers the essential functionality. However, it lacks details on signal semantics, edge cases, or examples, which could help an agent use it correctly in varied contexts.

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% and both parameters are described with example values. However, the description adds no additional meaning beyond the schema—it does not explain how country or line affect the signal or what each parameter does. Baseline 3 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?

Description clearly states the tool returns a buy_now/monitor/wait signal based on specific metrics, answering the core question 'when should I buy?'. The verb 'Returns' and resource 'signal' make the action unambiguous, and it distinguishes itself from siblings like market_price_risk by focusing on procurement timing.

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

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

The description implies use for purchase timing decisions but provides no explicit comparison to siblings like market_optimize_purchase or market_price_risk. It does not specify when not to use this tool or provide alternative tools for related tasks.

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 and no output schema, the description bears full responsibility for behavioral disclosure. It does not mention rate limits, permissions, return format, or whether parameters are required (both are optional in schema). Only the list of scores is given, lacking 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 a single, concise sentence that directly states what the tool does. It wastes no words, though it could benefit from a more structured format (e.g., bullet points for the score types).

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

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

Given the complexity of 'composite moat scores' and the absence of output schema or annotations, the description is inadequate. It doesn't explain the meaning, range, or usage of the five scores, nor does it clarify the effect of leaving parameters empty.

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% (both parameters have descriptions), but those descriptions are merely example values (e.g., 'PE, AR, MX, BR, CO, CL' for country), not semantic explanations. The tool description adds no additional parameter context, so little value beyond the schema.

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

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

The description clearly states the tool provides composite moat scores with five named components (retail_aggression, price_fairness, etc.), distinguishing it from sibling tools that focus on specific areas like affordability or inflation. However, it doesn't explicitly state the action (e.g., 'Get' or 'Retrieve') or explain what 'moat scores' represent.

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

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

No guidance is provided on when to use this tool versus siblings such as market_affordability or market_inflation. The description implies it's for composite scores, but fails to specify context or 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?

With no annotations, description carries burden. It mentions timeout behavior and links store_key to market_add, but doesn't disclose rate limits, auth, or other behavioral traits.

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?

Concise, no fluff. Includes key details in few sentences. Could be slightly more structured but acceptable.

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 scope, return fields, and key parameter interactions. References other tool (market_add). Adequate given 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 coverage is 80%. Description adds value: hints for country (avoid timeouts), line examples, and store_key's role in market_add. Compensates beyond baseline 3.

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 searches products across 41 retailers in 8 countries, with specific output fields. However, it does not explicitly distinguish from sibling tools like market_discover, which may have similar scope.

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

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

Provides some guidance: 'Prefer setting country to avoid timeouts' and 'Prefer this over scraping.' But lacks explicit when-not-to-use or alternatives among siblings.

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

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

No annotations are provided, and the description does not disclose behavioral traits like read-only nature, refresh frequency, or side effects. It only lists output fields, missing critical safety 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 short and front-loaded with a category tag. It efficiently lists key outputs, though it could benefit from minor restructuring for clarity.

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 or annotations, the description is the sole source of information. While it mentions four metrics, it lacks explanation of 'data moat health' and potential additional outputs, leaving some 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?

There are no parameters, so the schema fully describes them. The baseline of 4 applies as the description adds no parameter-specific information, but none 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?

The description specifies metrics like total prices, active stores, tracked products, and last refresh, clearly indicating it provides data moat health statistics. It distinguishes from siblings such as market_search or market_add by focusing on aggregate 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?

No guidance on when to use this tool versus alternatives. It lacks context like prerequisites or exclusions, leaving the agent to infer usage from the name and metrics alone.

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

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

With no annotations, the description bears the full burden. It implies a read-only retrieval but does not explicitly confirm no side effects, authentication needs, or data freshness.

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, front-loaded sentence with no wasted words. Every part is meaningful.

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 adequately lists the key components of a subscription plan. It could mention more details like usage or expiration but is sufficient for a simple info tool.

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

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

There are no parameters; schema coverage is 100%. Per calibration, 0 parameters yields a baseline of 4. The description adds no parameter info, and none 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?

The description clearly states the tool retrieves the current subscription plan for the account, listing specific details (tier, rate limits, API keys). It distinguishes itself from sibling tools like market_whoami or market_login.

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. The description does not mention prerequisites, limitations, 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?

No annotations provided, so description carries the burden. It mentions 'unit-normalized savings and Nutri-Score tradeoffs' hinting at output traits, but lacks details on response format, auth needs, or potential side effects. Adequate but minimal.

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, no wasted words, front-loaded with action and context.

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?

No output schema, no annotations. Description gives purpose and usage context but does not explain return structure or edge cases. Sufficient for a simple data retrieval tool but could be more complete.

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

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

Schema covers 75% of parameters (3 of 4 described). Description adds no additional parameter context beyond the schema. Baseline is neutral as coverage is moderate.

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 'Product substitutes with unit-normalized savings and Nutri-Score tradeoffs' and gives specific usage context 'when exact SKU unavailable or optimizing basket'. It distinguishes from siblings like market_barcode or market_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?

Explicitly states when to use: 'Use when exact SKU unavailable or optimizing basket'. It implies alternatives but does not name them explicitly, so a point off.

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

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

With no annotations, the description carries full burden. It discloses OCR scanning and price comparison, and that submit_to_crowd persists validation. However, it does not mention authentication needs, rate limits, or potential side effects of submission, leaving gaps in behavioral understanding.

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 contains no fluff. Every sentence adds value: the first states the action, the second provides critical usage guidance.

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 should explain the return value or how results are presented. It lacks details on what happens after scanning and comparing (e.g., output format, next steps), making it incomplete for an OCR-based tool.

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

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

Schema coverage is 100%. The description adds context for 'url' ('Pass a public image URL') and 'submit_to_crowd' ('persist moat validation'), but does not enhance meaning for 'country' or 'line_items' beyond the schema. This adds marginal value over the schema, meeting baseline expectations.

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 scans a purchase receipt via OCR and compares prices against a 'data moat', using a specific verb and resource. It distinguishes from siblings like market_barcode (barcode scan) and market_compare (compare items) by focusing on receipt OCR.

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 tells how to use it ('Pass a public image URL', 'Set submit_to_crowd to persist') but does not explicitly state when to use this tool over alternatives or when not to use it. The '[Advanced]' tag hints at complexity but lacks concrete 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 provided. The description does not mention whether the tool is read-only, if it requires authentication, rate limits, or any side effects. It only states the output type without behavioral 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 very concise (one sentence), but it is too sparse. It could be restructured to include parameter guidance or usage hints without adding verbosity.

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 output schema, no parameter descriptions, and no annotations, the description is incomplete. It does not help an agent understand how to use the parameters or what the 'largest price movement' means (e.g., absolute or percentage, direction).

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 3 parameters (country, line, limit) with 0% description coverage in the schema. The description does not explain any parameter meanings, acceptable values, or defaults beyond the schema's bare names and types. The default limit of 10 is not mentioned.

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 that the tool returns products with the largest price movement in the last 7 days. The '[Intel]' prefix hints at usage context, though not explicit. It distinguishes from siblings like 'market_price_alerts' or 'market_inflation' by focusing on recent price movement magnitude.

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 versus alternatives. The description does not mention when 'Intel' tools are appropriate, or how it differs from other market tools like 'market_scores' or 'market_stats'.

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

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

With no annotations, the description carries full burden. It clearly states the tool returns username and subscription tier, implying read-only and safe behavior. Could mention authentication requirement or error cases, but sufficient for a simple identity check.

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?

Extremely concise: one sentence with a bracketed category prefix. No wasted words; every element earns its place.

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

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

Given zero parameters, no output schema, and simple purpose, the description is sufficient. It covers what the tool does and returns. Could mention authentication prerequisite or error handling, but not required for 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?

No parameters exist (schema coverage 100% for empty), so baseline is 4. Description adds no parameter info, but none 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?

The description clearly states it verifies identity and returns username and subscription tier for the authenticated user. The bracket prefix '[Account]' and specific verb-resource pair differentiate it from siblings like market_login or market_preferences.

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 checking authenticated user identity but does not explicitly state when to use vs alternatives or provide when-not scenarios. No exclusions or alternative tool references.

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