kari catalog

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

Beyond the readOnly/openWorld annotations, the description discloses result-shaping behavior an agent cannot get from the schema alone: results are capped at 10 stores and quantities are deliberately not disclosed. That is meaningful context about the output contract, though it says nothing about latency, auth, or failure modes.

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 short sentences, front-loaded with the core question ('which stores can hand over this size'), followed by the scoping constraints. Slightly telegraphic phrasing in the first sentence, but nothing is wasted or buried.

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 annotations covering the safety profile and an output schema handling return values, the description only needs to add what structure cannot: the pickup semantics, the 10-store cap, and the quantity-disclosure policy. It covers those adequately; a note on empty/no-match results would make it fully complete.

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 each parameter documented in-schema (size, articul, city_id, country with enum labels). The description's 'Omit size for items without sizes' merely restates the schema's size description, so it adds no incremental meaning. 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 states a specific capability: finding which kari stores in a given city can hand over a product in a given size, with the 'pickup' qualifier clarifying the fulfillment mode. It is distinguishable from find_stores (store listing) and get_product/search_products (catalog lookups), though it does not name those siblings 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?

Usage is largely implied rather than stated: the agent must infer that articul comes from search_products and city_id from find_city (the schema supplies those links). The one explicit guideline, 'Omit size for items without sizes,' is a genuine conditional. No when-not or alternative-tool guidance is given.

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 readOnly, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: matching is by partial name and results are capped at 10 with city_id returned, though the return detail is partly redundant given an 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?

Two short sentences, no filler, with the scoping constraint and the result cap both front-loaded. 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 two-parameter read-only lookup with an output schema and full annotation coverage, the description is nearly sufficient. It could mention behavior on zero matches or the country constraint, but nothing essential for a correct call 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 100%, so the baseline is 3. The description clarifies that 'query' is a substring match ('by part of its name'), which adds a little meaning, but the required 'country' enum and its effect on the search are left entirely to 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 and resource (find a city) scoped to 'where kari operates', which separates it from a generic geocoder. It does not explicitly name or contrast with siblings like find_stores, but the business scope makes the intent 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?

Usage is only implied: the scoping to 'where kari operates' hints this is a lookup step preceding store/availability calls, but there is no explicit when-to-use or when-not statement and no alternative is named.

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 establish readOnly, non-destructive and closed-world behavior, so the bar is lower. The description adds genuinely useful operational context beyond them: it surfaces the filtering dimensions and the 10-stores-per-page pagination contract, which an agent needs when deciding whether to page through results.

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, each earning its place: what is listed and what comes back, what can be filtered, and the page size. Purpose is front-loaded with zero 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?

An output schema exists, so return-value documentation is not required, and the read-only annotations cover the safety profile. The description covers scope, filtering and pagination adequately; the only gap is not mentioning the find_city dependency relationship, which the schema does carry via city_id.

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 baseline is 3. The description restates the query filter scope and page size but adds no syntax or format detail beyond the schema's own per-parameter descriptions ('Part of the store name, address, mall or metro station', 'Page number, from 1').

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 kari stores in a city') and even enumerates the returned fields (address, opening hours, coordinates), which distinguishes it from get_product/search_products. It does not name or explicitly contrast any sibling, so it falls short of a 5, but the purpose 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?

The description implies when it applies ('in a city', 'Filter by part of the name, address, mall or metro station'), which tells the agent what kind of lookup this handles. However, it never states when to prefer it over check_availability or how it relates to find_city (the required city_id dependency is only in the schema), so guidance is implied rather than explicit.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral detail beyond structured fields — that items lacking sizes return an empty sizes list — which handles an edge case the agent would otherwise misread as missing data, but nothing about permissions, caching, or failure modes.

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 short sentences with zero filler; the core purpose and the returned-field list are front-loaded, and the second sentence exists only to resolve a real ambiguity about empty sizes. Nothing could be cut without losing 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?

An output schema already exists, so return-shape explanation is unnecessary, and annotations cover safety; the description supplies the field inventory and one data-edge case. Only the when-to-use routing relative to search_products/check_availability is left to inference.

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 every parameter (articul, city_id, country) is already documented, including the default-for-city_id and the country enum values. The description mentions articul and city availability implicitly but adds no syntax, format, or defaulting information the schema does not already carry.

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 ('Product details by articul') and enumerates the returned fields (price, images, color, composition, rating, sizes/availability), so an agent knows exactly what it retrieves. It does not name search_products as the feeder tool in the description text itself (that routing hint only lives in the schema), so sibling differentiation is only partial.

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: knowing that 'articul' comes from search_products and 'city_id' from find_city tells the agent this is the follow-up detail call, but the description never says when to use this instead of search_products or check_availability. No exclusions or prerequisites are given.

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, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond them: what the response contains and the caveat that the size filter reflects the model's size range rather than available inventory — a misuse trap the annotations cannot express.

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 dense sentences, front-loaded with purpose before caveats, and each sentence earns its place: catalog scope, return contents, and the size/stock distinction. No filler or restatement of the name.

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?

An output schema exists, so return-value detail is optional, yet the description still summarizes it helpfully. Combined with siblings (get_product, check_availability, find_city) and schema-documented defaults like city_id and limit, the agent has enough to call it correctly; only the relationship between country/city filtering is left implicit.

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 60%; the schema's own 'size' description ('Size as on the website') is ambiguous, and the description meaningfully augments it by clarifying it is a model size range, not stock. It adds no meaning for the undocumented sort, brand, price_min, and price_max parameters, so it compensates for the most critical gap but not all of them.

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 opens with a specific verb+resource+scope: searching the 'kari catalog (shoes, clothing, bags, accessories)' with filters. It also names what the result contains (price, size range, website link), so an agent knows exactly what this tool produces and how it differs from product-detail siblings.

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 resolves the most dangerous ambiguity explicitly — 'sizes is the size range of the model, not stock: check stock with get_product or check_availability' — which is both a when-not condition and a named alternative. It does not, however, say when to prefer this search over a direct get_product lookup by name, leaving that choice to inference.

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