Feedico: coupons, deals & products

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

Annotations already declare readOnlyHint and openWorldHint, and the description usefully adds that the link is tracked (click/sales attribution, per the sub parameter described in the schema). However it does not disclose link persistence or expiry, idempotency of repeated calls, or rate limits, and the verb "Create" sits in mild tension with readOnlyHint even though generating a URL is effectively side-effect free.

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 the core action and the optional deep-link case front-loaded, followed immediately by the input-source instruction. No filler, nothing repeated from the schema or title.

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 single-required-parameter tool with full schema coverage and no output schema, the description covers purpose, input source, and the optional page targeting. The only gap is that with no output schema it never states what is returned (a URL string) or whether the link is reusable.

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 carries all three parameters, including the store id format and the sub identifier constraints. The description re-anchors store ("from search_stores") and clarifies pageUrl as a product or category page on the store's own site, but adds only marginal meaning beyond 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?

Specific verb and resource ("Create a tracked link to a store") with the scope spelled out, including the optional deep-link to one product or category page. An agent can immediately distinguish this from the sibling search_* tools, which retrieve data rather than produce a link.

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 establishes the input flow explicitly: "Use the store id from search_stores," telling the agent to obtain the identifier from a sibling tool first. It does not state when to use the optional pageUrl or sub, and there is no named alternative to avoid, so it stops short of full when/when-not guidance.

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 and openWorldHint, so the safety profile is covered. The description adds real behavioral value by disclosing the return contents (code, title, end date, store) and noting that the link is tracked, which matters for an open-world search with no output schema. It still says nothing about result ranking or empty-result 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?

Two sentences, both front-loaded: the core capability first, then a routing example. Every clause carries information — what it finds, how to filter it, and what it returns — 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?

With no output schema, the description usefully summarizes the returned fields, and the annotations cover safety and open-world reach. It is nearly complete for a 5-parameter search, though limit/pagination behavior and how results are ordered are left to the schema.

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 all five parameters (limit, query, store, countries, endingWithinDays) are already documented with examples and bounds. The description restates store/keyword filtering but adds no syntax, format, or combination semantics beyond the schema, so the 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 verb and resource ('Find active coupon codes and deals') and names the two filter dimensions (store name and/or keyword), so the agent knows exactly what this tool retrieves. It does not explicitly contrast itself with siblings like search_products or search_stores, but the coupon-specific resource makes it distinguishable in practice.

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 gives concrete usage context with a worked example ('is there a discount code for Nike?'), which clearly signals when to reach for this tool. It stops short of naming alternatives or exclusions, so the agent must infer that product/store lookups belong to the sibling tools.

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 the safety profile (readOnlyHint=true, openWorldHint=true), so the description's real contribution is disclosing the result payload: price, sale price, store, image and a tracked product link, plus the fact that data comes from affiliate feeds. It does not cover auth requirements, rate limits, or result ordering/cap 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?

Two tight sentences, zero filler. Capability and scope are front-loaded, and the return-value sentence follows naturally without restating the title or 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?

With 9 optional params, no output schema, and moderate schema coverage, the description compensates well by enumerating search modes and listing returned fields. It falls short only on behavior an agent would want before calling — result limit interaction, offer deduplication, or country/price filter interaction.

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%, so the schema already documents most inputs (sku, store, countries, onSale, limit). The description's mention of keyword, brand, store, SKU and price filters maps onto those params but adds no syntax, format, or interaction rules beyond what the schema says.

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 ('Search millions of products from affiliate feeds') and enumerates the search axes (keyword, brand, store, exact SKU/part number) plus price filters. The resource noun 'products' implicitly separates it from search_coupons and search_stores, but no sibling is named, so routing is inferred rather than stated.

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?

Listing the searchable axes (keyword vs. brand vs. store vs. exact SKU) implies which parameter mode to pick for a given intent. However, there is no explicit when-to-use statement, no exclusions, and no pointer to the sibling tools (search_stores, search_coupons, get_store_link) that share this problem space.

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 openWorldHint=true, so safety is covered. The description still adds real behavioral value by disclosing result content (active coupon count, commission rate with the conditional 'when the network publishes it'), which signals fields may be absent for some stores. No output schema exists, so surfacing these traits is genuinely useful.

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 begins with the action and resource before enumerating result fields. It is somewhat dense with a long trailing clause list, but every clause earns its place by describing what is returned where no output schema exists.

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, describing the returned fields is essential and the description does it well, including conditional availability of commission data. What is missing is result ordering/pagination semantics and routing guidance versus get_store_link, which keeps it out of the top band.

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 query, limit, countries, and cashbackOnly are all documented in the schema. The description adds no parameter-level meaning beyond that, so the 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+resource ('Find stores (merchants) by name or domain') and clarifies the search key, which cleanly distinguishes it from the coupon and product search siblings. It does not name or contrast with get_store_link, even though it advertises returning 'a tracked link to the store,' leaving mild overlap unaddressed.

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 prerequisites, and no mention of alternatives. Worse, the promise of a 'tracked link' overlaps with the sibling get_store_link without explaining when the agent should prefer one over the other.

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