Swissgroceries MCP

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

No annotations, so the description carries the full burden. It valuably discloses the unsupported-chain error behavior, but says nothing about auth requirements, rate limits, or the cost/latency of the Nominatim geocoding path (only the schema hints at preferring zip/lat/lng for speed).

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?

Front-loaded core capability followed by filtering options, caveat, and examples — all earning their place. The closing example list is slightly redundant with the schema's own description text but stays short.

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?

Reasonable for a read-style lookup, but with no annotations and no output schema the description never states the return shape (store list with stock status?) or whether results are live. An agent can call it, but is left inferring 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?

Schema description coverage is 100%, so chain, productId, near, and storeId are already fully documented including precedence and the productId provenance. The description merely restates the proximity and single-store options, adding no syntax or format detail 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?

States a specific verb+resource+scope: which stores of a given chain carry a specific product in stock. The illustrative queries ("which Coop has item X in stock?") make it distinguishable from sibling find_stores and search_products.

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 the two usage modes (proximity filter vs. single store by ID), gives example queries, and warns that unsupported chains error out. It stops short of naming find_stores/search_products as the alternatives to use when the question is about stores or products rather than stock.

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 disclosure burden. It does state the return fields (name, address, chain, location, hours 'where available') and that a ZIP, coordinates, or free-text address are all accepted, which is genuinely useful. However it omits any mention of geocoding latency/cost, rate limits, permission requirements, or result-count/pagination behavior, leaving notable gaps for a no-annotation 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?

Three tight sentences: purpose first, then input modes, then return shape, then usage examples. Every sentence earns its place with no redundant restatement.

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, and the description compensates by enumerating the returned fields, so an agent knows what to expect. Input modes are fully covered. It could go slightly further on result limits or the store-vs-stock distinction, but it is essentially complete for this complexity level.

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 all three parameters (near variants, chains, radiusKm) are already fully documented in the schema, including defaults, the 1–50 km bound, and the coopcity opt-in rule. The description adds no syntax or semantic detail beyond what the schema provides; 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?

Specific verb+resource ('Find grocery stores') with scope qualifiers (near a location, filtered by chain and radius). It is clearly distinguishable from siblings like search_products, get_product, and find_stock, which operate on products/stock rather than store locations.

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?

Gives concrete trigger phrases ('find a Migros near me', 'which Coop branches are in 8001?') and a sequencing cue ('before checking stock') that implies chaining with find_stock. It stops short of explicitly naming the sibling to use for stock lookups, so no true when-not/alternative statement.

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, and it does disclose notable behavior: the response shape { product, fetchedAt, fromCache } and that fromCache indicates caching/freshness. It stops short of covering failure modes, permissions, 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?

Purpose and return shape are front-loaded, and the trailing example prompts are short and illustrative. It is slightly longer than strictly needed, but every sentence carries some routing or behavioral 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?

With no output schema, the description usefully enumerates the returned fields (price, brand, size, unit price, tags, category, image, promotions), which is the right compensation. Remaining gap is error behavior for invalid or unknown IDs.

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% and both parameters are already documented (chain enum, chain-specific ID). The description's 'chain + product ID pair' framing reinforces the composite-key semantics but adds little the schema doesn't already say.

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?

States a specific verb and resource ('Fetch full product details for a specific chain + product ID pair') and immediately distinguishes itself from search_products by being the drill-down step.

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 names the prerequisite source of IDs ('Obtain product IDs from search_products') and characterizes the use case ('drilling into a search result'), with concrete example queries. It doesn't explicitly exclude other siblings, but no genuine alternative exists for fetching full details.

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: 'List' implies a read-only operation and it discloses the return fields (name, discount, validity dates, applicable stores), which is useful since no output schema exists. However, it says nothing about pagination, result caps, rate limits, or the opt-in behavior of some chains, so behavioral disclosure is only partial.

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

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

Three sentences, front-loaded with the core action, then filters, then return shape, then usage examples. Every sentence earns its place and there is 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?

For a zero-required-param read tool with no annotations and no output schema, the description covers what it does, what can be filtered, and what is returned. Missing only operational details such as pagination or limits, which are minor for this shape.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters thoroughly (including the coopcity opt-in nuance and the find_stores reference). The description's filter summary ('chain, keyword, store ID, or how many days until the promotion expires') largely restates the schema without adding syntax or format detail.

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?

States a specific verb and resource ('List current promotional deals across configured Swiss grocery chains') and enumerates the filter dimensions. The domain is clearly distinct from siblings like search_products and find_stores, though no sibling is named explicitly for differentiation.

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 'Use for ...' clause with three concrete example queries ('what is on sale this week?', 'any Migros deals on cheese?', 'promotions ending today') gives clear context for invocation. It stops short of naming alternatives or when-not-to-use cases (e.g., use search_products for non-promotional items).

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, and it does disclose the probing mechanism (one trivial query per adapter) and the reported fields, which reassures the agent this is non-mutating. It omits that probing all adapters can take up to timeoutMs per chain (potentially tens of seconds), and never explicitly states the operation is read-only.

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 tight sentences: the first defines behavior and output, the second defines when to reach for it. Nothing is wasted and the core capability 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?

Zero required parameters, no output schema, and complete schema descriptions mean the description only needs to explain purpose, trigger, and return shape — all of which it does. Nothing an agent needs in order to call it correctly is missing.

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%, and both 'chains' (default: all configured) and 'timeoutMs' (default 5000, max 30000) are documented in the schema itself. The description adds no parameter-level meaning, so the 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?

States a specific verb (probe), resource (each registered chain adapter), mechanism (trivial query), and return payload (status, latency, capability flags). It is unmistakably distinct from the sibling tools, all of which fetch store/product/promotion data rather than adapter diagnostics.

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?

Gives two explicit trigger conditions: a chain appearing to be missing from results, and debugging adapter problems. No when-not guidance or named alternative is given, but the diagnostic framing implicitly excludes normal search workflows.

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 disclosure burden. It does reveal return behavior ('Returns a primary plan plus alternatives') and the semantics of the three strategies including the stop penalty, which is useful. It does not state that the operation is read-only/non-mutating, whether it hits live chain APIs, or any limits — significant omissions given zero annotation coverage.

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?

Four sentences, front-loaded with purpose, then behavior, then usage trigger, then strategy summary. Efficient overall, though the strategy list duplicates the strategy enum's schema description and could be trimmed.

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 fairly complex composite tool (6 params, nested item objects, three strategies) with no output schema and no annotations, the description says the result is 'a primary plan plus alternatives' but never sketches what that plan contains or how cost/stops are reported. It is adequate to invoke, but not complete enough to predict the response shape.

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

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

Schema description coverage is 100%, so the schema already documents every parameter including the strategy enum and the splitPenaltyChf semantics. The description's note that items can be generic or pinned to a SKU, and its strategy recap, largely restate what the schema already says, so the 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?

The description gives a specific verb and resource — 'Plan a multi-store shopping trip near a location, picking the best products across configured Swiss grocery chains' — which is a composite planning task no sibling (search_products, find_stores) performs. It is clear and distinctive, but it never names or contrasts with the sibling tools an agent might otherwise reach for.

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 gives a concrete trigger: 'Use when the user gives a list of items and asks "where should I shop?" or "what's cheapest?"'. That is strong context, but there is no explicit exclusion (e.g., 'for a single product lookup use search_products instead'), so the agent must infer the boundary.

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 and does so well: it discloses failure semantics (empty array + entry in `errors` with code/reason on bot protection or outage), data-freshness reporting via a `sources` map (fetchedAt + fromCache), per-chain grouping, promotion info, and the opt-in behavior of coopcity. This is exactly the operational context an agent needs beyond structured fields.

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 dense paragraph that is well front-loaded with the core purpose before drilling into chain semantics, return format, and failure handling. Every clause carries information, though the paragraph is long enough that the return-format and error details could be trimmed or split 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?

Despite having no output schema, the description explains the result shape (byChain grouping, normalised price/unit price/size/promotion, sources freshness, errors array) and the key edge cases (failed chains produce empty arrays, coopcity opt-in). Nothing essential for correct invocation or result interpretation appears missing.

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 baseline is 3, but the description adds real meaning for the `chains` parameter by explaining what coop vs coopcity actually cover and that coopcity is silently skipped when `chains` is omitted. Filters (price, size, tags) are summarized but the schema already details them, so this is a modest lift above baseline.

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?

Starts with a specific verb+resource and scope: 'Search for products across configured Swiss grocery chains ... by keyword.' It names the chains and distinguishes the coop vs coopcity assortments, so an agent can tell it apart from find_stores, get_product, and get_promotions without opening schemas.

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 concrete use cases ('find organic milk under 2 CHF', 'compare pasta prices') and explicit conditional guidance for the opt-in coopcity chain and for checking `errors` before reporting empty results. It stops short of stating when to prefer get_product or get_promotions over this search tool, so it lacks explicit sibling exclusion.

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