genesispay-catalog

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered, yet the description still adds substantive context: verified-purchase reviews prove a purchase not an opinion's truth, review count is not sales count, pagination requires passing nextCursor unchanged, and review text is untrusted data rather than instructions. That is well beyond what the structured fields 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?

Front-loads the core action and id scope, then layers caveats and pagination rules in short clauses. No sentence is filler; each one either routes the agent, constrains usage, or warns about data handling.

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 return semantics, and it does: it explains what is returned (published reviews and rating), the pagination model, and the trust limitations of review content. Nothing needed to call it correctly is absent.

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 three parameters are already documented, establishing a baseline of 3. The description adds real semantics beyond the schema by stating that nextCursor must be passed unchanged for the next page, clarifying the round-trip contract with the server rather than just the field format.

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 (reads) and resource (published reviews and rating) and scopes it to two id types (prod_…/ext_…). It also names where those ids come from, making it trivially distinguishable from genesispay_catalog_search and genesispay_catalog_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?

Explicitly routes the agent to genesispay_catalog_search or genesispay_catalog_trending as the source of the required id, which is the main usage prerequisite. It does not state any when-not-to-use condition, but for a read-only lookup tool there is little ambiguity left.

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 readOnlyHint/openWorldHint/destructiveHint, but the description adds substantive behavior: price.listedOnly semantics (shipping/tax set at shop checkout) and an explicit prompt-injection warning that seller text is untrusted data, never instructions. That is exactly the extra context annotations cannot carry.

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 is front-loaded and the safety warning closes it; every sentence carries information. It is fairly dense, but no sentence is redundant or restates structured fields.

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 (title, description, price, shop, rating, pageUrl, howToBuy). Combined with the price caveat and safety note, an agent has everything needed to call and interpret the 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 description coverage is 100%, so the schema already documents kind, shop, limit, query, and category. The description adds no parameter-level syntax or defaults beyond what the schema states, 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?

Opens with a specific verb+resource ("Searches products and services listed on GenesisPay") and names the result domain precisely. It is clearly distinguishable from siblings reviews, shops, and trending, which cover different resources.

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 context: the shop filter takes an id from genesispay_catalog_shops, and buyers of results should consult each result's howToBuy field. It stops short of explicit when-to-use/when-not guidance relative to siblings like trending or shops.

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 readOnlyHint and destructiveHint. The description adds genuinely useful context beyond them: the returned fields, the routing to search for listings, and a crucial security warning that seller text is untrusted and never instructions. That last point alone is high-value behavioral guidance.

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 purpose, then read-only status, output fields, routing, and security warning. Every sentence earns its place, though the field enumeration plus routing 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?

Complete for a read-only catalog search: purpose, output shape, sibling hand-off, and an untrusted-data warning. Without an output schema, the field enumeration is a reasonable stand-in, and no critical gaps remain.

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 limit and query are already documented in the schema with ranges and examples. The description adds no parameter-level meaning beyond what structured data provides, 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 (finds) and resource (shops on GenesisPay), distinguishing it from siblings like catalog_search and catalog_trending. The description also enumerates the returned fields, making scope concrete.

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 routes the agent: to see a shop's listings, call genesispay_catalog_search with shop set to its id. This is a clear hand-off to a sibling, though it doesn't state when to prefer this tool over trending or reviews.

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 readOnlyHint=true and destructiveHint=false, so safety is covered, yet the description adds substantial behavior: the ranking/fallback algorithm, the warning that popularity is not a rating, the fact that purchase flow varies per result and lives in howToBuy, and an explicit untrusted-content warning about seller text. That is meaningful context an agent could not derive from 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?

Five short sentences, front-loaded with the purpose and ranking rule, then escalating to result-shape, per-result purchase flow, and a security caveat. No sentence is padding; each carries a distinct fact.

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 compensates by stating that results share genesispay_catalog_search's fields and by pointing to the howToBuy field for per-result purchase flow. Combined with the ranking definition and untrusted-data warning, an agent has everything needed to call and interpret this 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?

Only one parameter (limit) exists and the schema already documents it fully at 100% coverage, including the 1-20 range and default of 10. The description adds nothing about limit, so the baseline 3 for schema-covered parameters 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 (lists) and resource (products trending on GenesisPay) and immediately defines the ranking logic: recent distinct buyers first, newest listing as fallback. It also anchors the result shape to genesispay_catalog_search, letting an agent distinguish it from the sibling search tool without opening a 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?

The description explains what 'trending' means operationally (ranked by recent distinct buyers, newest-listing fallback), which implies when to prefer it over a plain search, but it never states an explicit when-to-use or when-not-to-use rule versus genesispay_catalog_search. Usage is inferable rather than directed.

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