Shopee MCP (via SEA MCP)

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

Annotations already declare this as a safe read (readOnlyHint true, destructiveHint false), and the description adds genuinely useful behavior: price is in market currency, coverage is incomplete, and a '{ data: null }' response means the listing is missing or not loaded. That null-handling detail is exactly the kind of context annotations cannot convey.

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

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

Three short sentences, front-loaded with the core purpose, followed by currency and null-response caveats. No filler; every clause carries operational 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 single-parameter read tool with no output schema, the description covers the essentials: what comes back (product plus shop and category), currency semantics, and how a missing listing manifests. Nothing critical for correct invocation 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 the single 'id' parameter is fully documented in the schema with a numeric-string pattern, so the schema carries the semantic load. The description's 'item id' restates it without adding format or constraint 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 (Fetch) and resource (one Shopee product) scoped by item id, and names the related entities returned (shop, category). The singular, id-based framing clearly distinguishes it from the sibling Shopee_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?

The phrase 'by item id' implies the tool is for direct lookup when an id is known, which contrasts with the search siblings, but there is no explicit statement of when to prefer this over Shopee_search_products or any prerequisites. Usage is implied rather than stated.

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

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

Annotations cover only the safety profile (readOnly, non-destructive), and the description adds substantial extra context: the data freshness horizon (22 Sep 2026), the fact that product coverage is partial (embedded products are only loaded listings, not full catalog), the meaning of itemCount, and the missing-result shape ({ data: null }).

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 with the core action and lookup keys, then caveats. Every sentence carries information, though the density of caveats makes it slightly longer than strictly necessary.

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 carries the burden of the return shape and does so (the null-data case, the embedded product completeness caveat, itemCount semantics, and the data freshness date). Nothing essential for calling 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 coverage is 75%, so id/country/productLimit are already documented. The description still adds meaning beyond the schema: id preferred over username, the username-missing edge case, and that embedded 'top stored products by units sold' relates to productLimit.

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 one Shopee shop') plus the two lookup modes, which clearly differentiates it from the sibling search tools (Shopee_search_shops, Shopee_search_products). An agent can select it without opening the schema.

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 explicit guidance on which key to use ('use id when you have it') and warns that a username lookup can miss a shop that exists. Strong context, though it never names search_shops as the alternative for discovery-style queries.

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?

Annotations already declare a safe read-only, non-destructive, closed-world operation. The description adds the AND semantics of filters and, importantly with no output schema present, the return shape { data, total, page, limit }, which is genuine 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?

Three tight sentences, front-loaded with purpose followed by usage and return shape. No filler and every clause carries information.

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

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

For a 7-param read tool with no output schema, the description supplies the return envelope and filter combination logic. Pagination and level parameters are left to the schema, which is acceptable but a small gap.

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 57%, but the description adds meaning beyond the schema by explaining the ANDing of filters and the parentId/rootsOnly relationship, which the schema documents only individually. It does not, however, clarify page/limit/level semantics.

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 ('Search the Shopee category tree'), which clearly distinguishes it from the product/shop siblings. An agent can immediately tell this operates on the category hierarchy rather than products or shops.

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 routing guidance within the tool: use parentId to list children, rootsOnly for top-level, and notes that filters are ANDed. It lacks explicit when-not-to-use or cross-sibling guidance, but the in-tool alternatives are clearly stated.

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

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

Annotations only declare the read-only safety profile, yet the description adds substantial behavioral context: prices are unconverted market currency, totals/rankings cover only stored listings rather than the full Shopee catalog, and a zero-match shop may still sell the item. It even summarizes the response shape, which matters because no output schema exists.

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?

Five tightly packed sentences, each carrying non-redundant information: purpose, filter logic, currency, coverage limitation, parameter hints, and return shape. The most decision-relevant facts (what it searches, what the results do not cover) are front-loaded with no filler.

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

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

For a 20-parameter search tool with no output schema and no annotations covering behavior, the description supplies the essentials: default sort, currency semantics, coverage caveats, key parameter hints, and the returned fields. It is slightly short of complete because pagination bounds (limit max 1000, page) and several sort/filter parameters go unaddressed.

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 45% across 20 parameters, so the description must compensate, and it does so selectively — it clarifies shopId usage, category child-inclusion, the indexed fields, and the country-to-currency mapping. However, roughly half the filters (minSold, location, priceMin/Max, minRating, sortBy/sortOrder, date bounds, pagination) receive no added meaning beyond their bare schema definitions.

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?

Opens with a specific verb+resource ('Search Shopee listings') that is unmistakably distinct from sibling tools that fetch a single product/shop or search shops and categories. It also names the default ranking and the currency behavior of results, so an agent knows both what it does and what it returns.

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 usage guidance ('Pass shopId when you already have a shop') and explains filter semantics ('Filters are ANDed', 'category matches a category name and includes its child categories'). The coverage caveat tells the agent when results may be misleading, but it never explicitly contrasts this tool with search_shops or get_product, so routing between siblings is left partly to inference.

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?

Annotations already cover the safety profile (readOnly, non-destructive), yet the description adds substantial behavioral context: filters are ANDed, results default-sort by followerCount, data completeness and a freshness date (22 Sep 2026), that some shops lack a username, and which fields are indexed for efficient scanning. It even discloses the response envelope despite there being no output schema.

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-loads the core purpose and defaults, then proceeds through per-parameter guidance and the return shape without filler. It is dense and runs long for a description, but each sentence carries distinct operational information rather than restating the schema.

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 22-parameter, zero-required search tool with no output schema, the description covers the missing pieces: filter combination semantics, default sort, data currency, null handling for username, and the { data, total, page, limit } return shape plus the Shopee url per row. An agent has everything needed to build a valid query.

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

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

With only 68% schema coverage, the description compensates with real semantics: registrationNumber interpretation varies by country (Indonesia NIB, Thailand company registration), street/city/district are substrings, city carries prefixes like 'KOTA JAKARTA UTARA', province is uppercase, and sortBy accepts any ShopeeShop column. This explains how to format values in ways the schema alone does not.

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

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

Opens with a specific verb+resource ('Search Shopee shops') and immediately states scope ('Shops are complete'), which distinguishes it from the singular Shopee_get_shop and from Shopee_search_products. Defaults and filter-combination behavior are stated up front.

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 actionable selection guidance for parameters ('Use registrationNumber for a legal id... Use username for an exact handle', 'set minFollowers or minRating when scanning a market'), which tells the agent how to route a given lookup. It never names a sibling tool or states when not to use this one, so it stops short of the explicit alternative-routing that earns a 5.

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