KaliCart Global (UCP Catalog)

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds valuable context: it reads live from the merchant bridge but falls back to an indexed snapshot if the merchant is unresponsive, and marks the snapshot as such. This goes beyond the annotations and helps the agent interpret result freshness, but it doesn't discuss auth or side effects beyond what annotations cover.

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 three sentences, front-loads the main purpose, then adds behavioral context about the live/snapshot fallback and purchase URL. Every sentence contributes useful information without padding. It is concise and well-structured.

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

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

Given the complex input schema with many optional fields and no output schema, the description is incomplete. It does not explain how filters, context, signals, or other parameters affect behavior, nor what the return payload looks like. The live/snapshot nuance is helpful, but for a tool of this complexity, a capable agent needs more detail on parameter usage and expected output.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions 'by product or variant id', which hints that the required `catalog.id` field holds that identifier, but it does not explain the structure of `catalog`, `meta`, `context`, `filters`, or other properties. For a tool with nested objects and many optional parameters, this is insufficient semantic support.

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

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

The description clearly states the tool retrieves product detail by product or variant id, mentioning variants, price, and availability. The verb 'get' and resource 'product detail' are specific. However, it does not explicitly differentiate from sibling tools like lookup_catalog or search_catalog, so an agent may not know when to pick this over them.

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 guidance on when to use this tool versus the siblings lookup_catalog or search_catalog. The description implies usage when you have an ID and want detail, but it never names alternatives or conditions. It only explains the live/snapshot behavior, not selection criteria.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds meaningful traits: live price/availability fetching vs indexed snapshot fallback, explicit indication when snapshot is used, and handling of unknown ids as not_found. This goes beyond the annotation baseline.

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 purpose and id format. Every sentence adds value, with no fluff 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?

The tool has nested objects and many optional parameters, and no output schema. The description covers only ids and source behavior, leaving the purpose of context, filters, and other fields unexplained. An agent would lack confidence in how to populate those optional parameters correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the ids parameter and its format, but completely ignores the meta, context, filters, signals, and attribution fields. The schema has no inline descriptions, so agents won't know their purpose without additional documentation.

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 (lookup), resource (products/variants by identifier), and scope (up to 25 ids) with exact id format examples. This distinguishes it clearly from siblings like get_product (single item) and search_catalog (query-based).

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?

Implies usage context: for direct id-based lookups rather than searching or fetching a single product. Mentions live vs snapshot behavior but does not explicitly contrast with sibling tools; however, the id-based nature makes the intended scenario clear.

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, idempotentHint, openWorldHint, and non-destructive, so the description's job is lighter. It still adds valuable behavioral context: results are indexed snapshots, every variant carries the seller, and price/stock must be verified via get_product. This is exactly the kind of non-obvious behavior an agent needs to know.

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 front-loads the purpose, then covers the key parameter semantics and ends with the crucial verification caveat. There is no filler, and every sentence contributes to correct invocation.

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 search tool with no output schema and a large nested input schema, the description covers the main invocation path and a key post-search behavior. It does not mention pagination or how to interpret the indexed snapshot structure beyond seller-on-variant, but the most important usage and verification context is present.

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

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

Schema description coverage is 0%, so the description carries the burden. It explains catalog.query as free text, filters.categories as canonical taxonomy values, filters.price as ISO 4217 minor units, and the default currency. It does not explain other schema fields like pagination, signals, or attribution, but the most decision-critical parameter semantics are covered.

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

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

The description clearly states this is a UCP Catalog search across independent WooCommerce merchants in KaliCart Global, which is a specific verb+resource. It also implicitly distinguishes from get_product by telling the agent to verify the chosen product there, making the search tool's role unmistakable.

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 concrete guidance: use catalog.query for free text, use canonical category values from products[].categories, and use get_product before quoting price or stock. It does not explicitly contrast with lookup_catalog, so there is a minor usage-selection gap, but the practical context is clear.

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