Search SuperCatch trading cards, prices, and stores; sign in to read your orders and watchlist.
Scored across 12 tools
Most tools target clearly distinct resources: product lookup vs store lookup vs marketplace search vs buyer vs seller scopes. The main overlap risk is search_docs vs search_account_docs (public vs permissioned docs), which descriptions disambiguate reasonably but could still be confused at a glance.
Names mix several conventions: get_*, lookup_*, search_*, my_*, and store_* prefixes. The store_ grouping for seller tools and search_ for docs/marketplace give some readable structure, but there is no single predictable verb_noun pattern.
Twelve tools is well within a comfortable range and each one covers a distinct facet (discovery, docs, product, store, buyer, seller). No obvious filler or redundancy.
The surface covers discovery, docs, product/store lookup, and read access to buyer orders, watchlist, and seller inventory/listings/orders. The main gap is that everything is read-only — no watchlist mutation, no order or listing create/update operations — though the apparent read-focused purpose limits the impact.
Return SuperCatch API catalog and OpenAPI discovery links.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, which fully cover the safety and side-effect profile, so the description only needs to add context. It does add that the response includes OpenAPI discovery links, but says nothing about whether the catalog is static, cached, or how the links should be followed.
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 front-loaded sentence with no filler; the verb and the returned content are the first words an agent reads. Nothing is redundant or padded.
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 no-parameter, read-only discovery tool with no output schema and full annotation coverage, the description supplies enough for correct invocation. It could still mention what the catalog is useful for (e.g. initial capability discovery) to round out the picture.
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 tool takes zero parameters and the schema is empty, so per the rubric the baseline is 4. There is no parameter surface for the description to clarify or obscure.
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?
Names a specific verb (Return) and a specific resource (SuperCatch API catalog plus OpenAPI discovery links), which is enough for an agent to tell this metadata/discovery tool apart from the commerce-oriented siblings (lookup_product, store_listings, my_orders). It stops short of explicitly contrasting itself with any sibling, so it is clear but not maximally differentiated.
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 contains no when-to-use, when-not-to-use, or alternative guidance. An agent must infer that this is the entry point for discovering API surface area before calling other tools, and nothing tells it how this relates to get_help_resource, the closest sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a public SuperCatch help, docs, or agent-access URL.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Public help or documentation topic. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds that the tool returns a public URL, which usefully clarifies the output nature, but it does not add further behavioral context such as response details or topic-resolution behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single efficient sentence with the verb and resource front-loaded. There is no wasted wording 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 one-parameter, read-only URL lookup, the description plus annotations and complete schema cover the essentials: it clearly states that a public URL is returned. The main remaining gap is lack of routing guidance versus related search 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 100%, and the single enum parameter is fully documented by the schema. The description adds little beyond indicating that the returned resource is a public help/docs/agent-access URL, so the 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 states a specific verb ('Return') and resource ('public SuperCatch help, docs, or agent-access URL'), and the title reinforces it. It is clear that the result is a URL, but it does not distinguish this tool from siblings such as search_docs or search_account_docs.
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?
There is no explicit when-to-use guidance, no exclusions, and no mention of alternatives like search_docs or search_account_docs. The required topic enum implies a known-topic lookup, but the description does not say why an agent should choose this over search-based siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return public SuperCatch product facts (title, effective price, condition, availability, active-listing count) plus the canonical URL for a product or listing slug.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Canonical product slug from a SuperCatch product URL or search result. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld=false, so the safety profile is covered. The description adds real value on top by specifying that only 'public' facts are returned and enumerating the returned fields, which matters because there is 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?
A single front-loaded sentence that names the return payload before the lookup key. No filler, 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?
With no output schema, the description correctly compensates by enumerating the return fields, and annotations cover the read-only/idempotent profile. It stops short of stating error behavior for an unknown or non-existent slug, which would complete the picture.
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. The description earns above baseline by stating the slug may be 'a product or listing slug', broadening the accepted input beyond the schema's 'canonical product slug' wording.
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 ('Return') and resource ('public SuperCatch product facts') and enumerates the exact payload (title, effective price, condition, availability, active-listing count, canonical URL). It is clearly distinct from lookup_store or search_marketplace, though it never names a sibling to sharpen the contrast.
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?
Usage is only implied: the mention of 'a product or listing slug' signals this is a slug-keyed lookup, and the schema notes the slug comes from a product URL or search result. There is no explicit when-to-use vs. when-to-use-something-else guidance, and no alternative tool is named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the public SuperCatch seller storefront URL for a username.
| Name | Required | Description | Default |
|---|---|---|---|
| username | Yes | Seller storefront username from a SuperCatch store URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and a closed world, so the safety profile is covered. The description adds that the returned storefront URL is 'public', which usefully signals no authentication or ownership is required, but it says nothing about failure behavior for an unknown or non-existent username.
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 front-loaded sentence with zero waste; the verb and the returned artifact lead before the scoping clause.
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 one-parameter lookup with full annotation coverage, the description states the input (username) and the output (public storefront URL), which suffices even without an output schema. The only omission is what happens when the username is unknown.
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 a single username parameter whose schema description ('Seller storefront username from a SuperCatch store URL') already explains the accepted value. The tool description adds no format, casing, or validation detail beyond the schema, so the baseline of 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 names a specific verb (return) and resource (public seller storefront URL) scoped to a username, so the agent can distinguish it from lookup_product or store_listings without opening any schema. It stops short of explicitly naming which sibling to use instead, but the resource is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this tool versus lookup_product, search_marketplace, or store_inventory, and no prerequisites or exclusions are given. The only guidance is implicit in the phrase 'for a username'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the signed-in user's purchases on SuperCatch, newest first: order id, status, item count, total, and date. Requires connecting a SuperCatch account.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return (1-50). | |
| cursor | No | Continue with nextCursor from the previous page, keeping the same status and limit. | |
| status | No | Only return orders in this status. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-structured context: newest-first ordering, the returned field set, and the account-connection requirement that gates invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, with the result shape and ordering front-loaded before the prerequisite. Every clause carries information an agent needs.
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 compensates by enumerating the returned fields, and pagination semantics live in the parameter descriptions. For a simple read-only list tool, nothing an agent needs 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 each parameter (limit, cursor, status enum) is already documented, so the baseline 3 applies. The description adds 'newest first' ordering context but no meaning beyond the schema for any individual parameter.
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 ('List'), resource ('the signed-in user's purchases on SuperCatch'), ordering (newest first) and the exact fields returned. The 'signed-in user's' scoping cleanly separates it from the sibling store_orders and my_watchlist without needing either schema opened.
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 a clear usage context plus a hard prerequisite: 'Requires connecting a SuperCatch account.' It doesn't name when-not conditions or point at an alternative sibling, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List listings on the signed-in user's SuperCatch watchlist with title, price, condition, listing status, any price-alert target, and product URL. Requires connecting a SuperCatch account.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return (1-50). | |
| cursor | No | Continue with nextCursor from the previous page, keeping the same status and limit. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds the non-obvious authentication prerequisite, which the annotations do not express. It does not discuss failure behavior when no account is connected, which keeps it from a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, with the core purpose front-loaded and the prerequisite trailing as a qualifier. Every clause carries information an agent needs.
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?
There is no output schema, but the description compensates by naming the returned fields (title, price, condition, status, price-alert target, URL), and pagination is fully specified in the schema. Auth requirement plus field enumeration make it complete for a two-parameter read 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%, with limit and cursor both documented including bounds and the nextCursor continuation pattern. The description adds no parameter detail beyond the schema, so 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 and resource ('List listings on the signed-in user's SuperCatch watchlist') and enumerates the fields returned. An agent can distinguish this from store_listings or search_marketplace purely from the description, since it scopes to the signed-in user's own watchlist.
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 a clear precondition ('Requires connecting a SuperCatch account') that determines whether the tool is callable at all. It does not explicitly contrast with sibling tools such as store_listings or search_marketplace, so exclusions are left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read your authorized documentation table of contents and cited sections. Private staff guides require current staff permissions. Requires separate docs:read consent.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | Search words; omit for the table of contents. | |
| documentId | No | Document id from the table of contents. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description adds real value beyond them: authorization scope ('authorized documentation'), staff-permission requirements for private guides, and a separate docs:read consent requirement — important preconditions an agent would otherwise miss.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short, front-loaded sentences with no filler: purpose first, then permission constraints. Slightly telegraphic phrasing ('authorized documentation table of contents') but every sentence 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?
The auth/permission picture is well covered, but with no output schema the description says nothing about what a result looks like, how sections are cited, or how limit interacts with the table of contents. Adequate for a read-only, no-required-param tool but with clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 67%, with query and documentId self-documented and only limit undescribed. The description echoes the table-of-contents behavior already stated in the query schema and adds no syntax, format, or limit/pagination semantics, so it neither compensates nor detracts.
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 ('Read') and resource ('authorized documentation table of contents and cited sections'), and the account-scoping is clear. It doesn't name or distinguish itself from siblings like search_docs or get_help_resource, leaving some ambiguity about which doc-search tool to pick.
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?
Usage is implied rather than stated: 'Private staff guides require current staff permissions' hints at a permission-gated use case, and the schema's 'omit for the table of contents' clarifies the query path. But there is no explicit when-to-use-this-vs-search_docs guidance or stated exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the public table of contents or find cited documentation summaries with content versions and review dates.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | Search words; omit for the table of contents. | |
| documentId | No | Document id from the table of contents. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description contributes that results are 'public' and carry content versions and review dates, which is useful since there is no output schema, but it stops short of describing result shape, ranking, or pagination beyond the limit parameter.
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?
One efficient sentence with no filler, and the primary mode (table of contents) is front-loaded. The trailing clause 'with content versions and review dates' is somewhat ambiguous in what it modifies, which keeps it from a 5.
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 3-parameter, all-optional search tool with rich annotations this is close to adequate, but with no output schema the description should say more about what a result contains, and it leaves the limit parameter and documentId workflow 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 coverage is 67%: query and documentId are already documented in the schema, including the key behavior of omitting query for the TOC. The description adds no meaning for limit (the one undocumented parameter) and does not explain how documentId is obtained beyond the schema's own note.
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 names a specific verb pair and resource: reading the public table of contents or finding documentation summaries. The word 'public' and 'documentation' distinguish it from siblings like search_account_docs and get_help_resource, though the dual-mode phrasing ('Read ... or find ...') is slightly compressed.
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 two modes imply when each path applies (TOC browsing vs. searched summaries), and the schema reinforces this with 'omit for the table of contents.' However, the description never explicitly states when to prefer this tool over search_account_docs or get_help_resource, leaving sibling selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search SuperCatch trading-card and collectibles listings. Returns the top results with title, active-listing count, list-price floor (or labeled market value when unlisted), product slug, and canonical URL.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results to return (1-10). | |
| query | Yes | Search terms, player name, set name, or product keywords. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the return shape (title, active-listing count, list-price floor or labeled market value when unlisted, product slug, canonical URL) and the fact that only top results are returned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero waste. The purpose is stated first and the return payload second, which is a well front-loaded structure for an agent deciding whether to call the 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?
With no output schema, the description correctly carries the burden of describing return fields, and it does so adequately. It stops short of covering result ordering rationale or behavior when nothing matches, but nothing essential to invoking the tool 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%, so both parameters (query, limit 1-10) are fully documented in the schema. The description adds no additional syntax, format, or matching-behavior guidance for the query string, so 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 names a specific verb and resource ('Search SuperCatch trading-card and collectibles listings') and even enumerates the returned fields, so the agent knows exactly what the tool does. It does not explicitly distinguish itself from the sibling lookup_product, which is the main gap for a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the verb 'search' and by the query parameter description ('search terms, player name, set name, or product keywords'), which hints at when this tool applies. However, there is no explicit statement of when to use this versus lookup_product or lookup_store, and no exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Summarize the signed-in seller's SuperCatch inventory: listing counts by status and total and available quantity. Requires connecting a SuperCatch account that owns an approved store.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new context beyond them: the account-connection and approved-store requirement, which is an auth/eligibility constraint an agent could not derive from the 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 tight sentences with no filler; the output scope (what is counted) is front-loaded before the access prerequisite. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters and no output schema, the description carries the burden and mostly discharges it by naming the metrics returned and the account prerequisite. It stops short of stating behavior when no approved store exists (error vs. empty result), a small remaining 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?
The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies no input is needed and instead specifies what is summarized.
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 (Summarize) and resource (the signed-in seller's SuperCatch inventory) plus the exact output shape: listing counts by status and total/available quantity. This distinguishes it from the item-level store_listings sibling by implication, but it never names that alternative explicitly.
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 a real precondition — a connected SuperCatch account that owns an approved store — which tells the agent when the tool is callable. It does not, however, contrast this aggregate-count tool with store_listings or store_orders, so an agent must infer which to pick.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the signed-in seller's SuperCatch store listings, newest first: status, condition, price, quantity, and product URL. Requires connecting a SuperCatch account that owns an approved store.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return (1-50). | |
| cursor | No | Continue with nextCursor from the previous page, keeping the same status and limit. | |
| status | No | Only return listings in this status. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive/closed-world behavior, so the bar is lower. The description still adds real value beyond them: the newest-first ordering, the exact projection of fields returned, and the account-ownership prerequisite that gates a successful call.
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 with zero filler; the resource scope and return fields are front-loaded and the prerequisite is placed last where it reads as a gate. Every clause carries information the agent can act on.
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 substitutes a field projection and states ordering, and the schema fully covers pagination and filtering. What remains unstated is how the list differs from store_inventory, the only gap an agent could plausibly stumble on.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so limit, cursor, and status are already fully documented including the enum values and the cursor-continuation rule. The description adds nothing parameter-specific beyond 'newest first' implying the default sort, so 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 ('List the signed-in seller's SuperCatch store listings') plus ordering ('newest first') and the exact fields returned (status, condition, price, quantity, product URL). It does not explicitly distinguish itself from the close sibling store_inventory, so an agent must infer the listings-vs-inventory boundary from the names alone.
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?
Usage is only implied by the scope phrase 'signed-in seller's store'; there is no explicit statement of when to call this versus store_inventory, store_orders, or lookup_store. The prerequisite ('Requires connecting a SuperCatch account that owns an approved store') is useful context but is an eligibility constraint, not a when-to-use rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List orders placed with the signed-in seller's SuperCatch store, newest first: order number, status, totals, tracking, and dates. Requires connecting a SuperCatch account that owns an approved store.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return (1-50). | |
| cursor | No | Continue with nextCursor from the previous page, keeping the same status and limit. | |
| status | No | Only return orders in this status. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful context the annotations don't carry: results are newest-first and access requires an approved store on a connected account.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero padding: what is returned and the sort order come first, the access prerequisite second. No redundancy with the title or annotations.
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?
There is no output schema, and the description partly compensates by naming the fields returned (order number, status, totals, tracking, dates). Combined with the fully documented schema this is largely complete, though a note on result volume/paging expectations would close the last 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 description coverage is 100%, so limit, cursor and status are already fully documented in the schema. The description adds no syntax or filtering detail beyond implying a newest-first ordering relevant to cursor paging, so 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 and resource ("List orders") scoped to the signed-in seller's SuperCatch store, and enumerates the returned fields plus sort order. It doesn't explicitly distinguish itself from the sibling my_orders (buyer-side orders) or lookup_store, leaving that distinction to inference.
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?
Adds a real prerequisite: a connected SuperCatch account that owns an approved store. However, it never says when to use this versus my_orders or lookup_store, and gives no guidance on filtering strategy despite exposing a status enum.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
my_orders1 field changedInput schema / properties / cursorAdded value: +{
+ "description": "Continue with nextCursor from the previous page, keeping the same status and limit.",
+ "maxLength": 512,
+ "type": "string"
+}my_watchlist1 field changedInput schema / properties / cursorAdded value: +{
+ "description": "Continue with nextCursor from the previous page, keeping the same status and limit.",
+ "maxLength": 512,
+ "type": "string"
+}store_listings1 field changedInput schema / properties / cursorAdded value: +{
+ "description": "Continue with nextCursor from the previous page, keeping the same status and limit.",
+ "maxLength": 512,
+ "type": "string"
+}store_orders1 field changedInput schema / properties / cursorAdded value: +{
+ "description": "Continue with nextCursor from the previous page, keeping the same status and limit.",
+ "maxLength": 512,
+ "type": "string"
+}get_help_resource1 field changedInput schema / properties / topic / enumPrevious value: -[
- "help",
- "getting-started",
- "buying",
- "selling",
- "shipping",
- "grading",
- "ai-recognition",
- "integrations",
- "faq",
- "agents"
-]New value: +[
+ "help",
+ "agents",
+ "docs",
+ "library",
+ "glossary",
+ "getting-started",
+ "buying",
+ "selling",
+ "ai-recognition",
+ "grading",
+ "shipping",
+ "integrations",
+ "api",
+ "flows",
+ "faq"
+]search_account_docssearch_docsget_api_catalogget_help_resourcelookup_productlookup_storemy_ordersmy_watchlistsearch_marketplacestore_inventorystore_listingsstore_ordersSports card database: card search, full set checklists, parallel lookup, card identification.
Search trading card prices, build carts and manage a CardNexus store. You pay on cardnexus.com.
Pokémon and One Piece card prices from eBay and Cardmarket in EUR, plus portfolio and favourites.
Sold prices for 16 million sports and trading cards, raw and graded, from HobbyCardIndex.
Add one secure layer between your agents and this server.
