FeedMyCart – shared grocery list

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

Annotations already declare destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds non-obvious behavior the annotations cannot convey: additions are visible to all household members, are labelled 'via AI', and re-calling duplicates items. It does not describe failure or ambiguity handling, so it is strong but not exhaustive.

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 tight sentences with zero filler. The core action is front-loaded, followed by parameter choice and then behavioral caveats in descending order of importance.

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, so the description carries the return-value burden, and it does not say what a successful call returns or how ambiguous natural-language text is resolved. For a two-parameter add tool whose annotations cover the safety profile, this is a minor gap rather than a blocking one.

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, but the description adds real meaning: `text` accepts natural language in any language (with a worked example), and `items`, when given, is used instead of `text` — an implicit precedence rule the schema's 'used instead of text when given' only hints at structurally.

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 ('Add') and resource ('products to the household's shared FeedMyCart shopping list') with scope ('one or more'). It is immediately distinguishable from the read-side siblings read_list, read_pantry, and search_deals.

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 clear context for choosing between the two input modes: use `text` for natural language in any language, or `items` for a structured list. It does not name explicit exclusions or point at a sibling for related tasks (e.g., reading or checking the list), 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 cover the safety profile (read-only, non-destructive, idempotent, closed-world), so the bar is lower. The description still adds genuinely non-obvious operational facts: the returned help text is in Dutch and includes direct in-app links, and it covers app-only features not reachable through the connection. These are real behavioral disclosures not inferable from the annotations or 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?

Two sentences, front-loaded with the core action and scope, then the enumerations and the language/link caveats. The long feature list is dense but each item earns its place by defining matching scope. Minor: it is somewhat list-heavy.

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 single-parameter, read-only lookup with full schema coverage, the description supplies the critical unknowns: topic domain, Dutch output language, presence of in-app links, and the app-only boundary. It is essentially complete. It could note that results may be empty when no help text matches, but that is a minor omission.

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 parameter is well documented (question, any language, with an example). The description adds no syntax, format, or matching behavior for the parameter beyond the domain list it will match against. With full schema coverage and one parameter, 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?

States a specific verb (Returns) and resource (FeedMyCart help text), and the parenthetical enumerates the topic domain (loyalty cards, receipt scanning, sharing, deals, pantry, recipes, offline use, costs, AI assistant connection). This clearly distinguishes it from the sibling tools add_to_list, read_list, read_pantry, and search_deals, which operate on actual data rather than app documentation.

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 scopes when it applies: questions 'about how the app works or whether a feature exists.' It also draws a boundary by stating it 'Covers features that are only available in the app, not through this connection,' signaling when this tool is inappropriate. No alternative tool is named for those app-only cases, but the usage context is otherwise 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, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds useful behavioral scope by specifying that it returns open items and recently checked-off items, which is not captured in 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?

A single, front-loaded sentence that states the resource and the returned content with no wasted words. It is appropriately sized for a simple zero-parameter read 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?

Given the simplicity, rich annotations, and absence of parameters, the description is largely complete. It explains what is read and what data is returned; only explicit alternative-routing guidance 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?

The tool has zero parameters, so the baseline is 4 per the rubric. The description does not need to explain parameter semantics, and the empty schema is consistent with a no-argument read operation.

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 (household's current shared FeedMyCart shopping list) with clear scope. The name and description distinguish it from write-oriented siblings like add_to_list and resource-oriented siblings like read_pantry.

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 by describing the list it reads, but does not explicitly say when to choose this tool over siblings such as read_pantry or add_to_list. No when-not conditions or prerequisites are provided.

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, so the safety profile is covered. The description adds real behavioral detail beyond them: the union of storage locations read and the ordering rule ('soonest expiry first'), which an agent could not infer from the 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?

Two sentences, zero waste, front-loaded with what is read before the value proposition. 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?

For a no-parameter, read-only tool with no output schema, the description supplies everything needed to call it correctly: what it returns (stock with quantities and expiry dates), the scope (pantry/fridge/freezer), and the ordering. Annotations cover the safety profile, leaving no meaningful 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 and schema coverage is 100%, so the baseline is 4. There is nothing parameter-related the description could add, and it does not misdescribe any input.

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 ('what the household has in stock') plus the covered locations (pantry, fridge, freezer), the fields returned (quantities, expiry dates), and the sort order. This is clearly distinguishable from siblings like read_list (shopping list) and search_deals.

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 usage contexts ('useful for meal ideas and to avoid buying what is already there'), which tells the agent when this tool is relevant. It stops short of naming alternatives or stating exclusions, so it is clear context rather than explicit when/when-not routing.

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/idempotent/non-destructive, yet the description adds meaningfully more: a per-household per-day search rate limit, the fact that only deals valid today are returned, and the language-dependence of match quality. These are behavioral constraints an agent cannot infer from the 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?

Purpose and scope lead, then return fields, input guidance, validity constraint and rate limit; every sentence carries distinct operational information with no filler 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?

With no output schema, the description still enumerates the returned fields (chain, product, deal price, regular price, last valid date) and covers the key constraints (today-only validity, rate limit, language of deal text), leaving nothing an agent needs before calling it.

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 baseline is 3; the description goes further by explaining the intended style of the query parameter (product word, language matching, 'koffie' example) and the reason it materially changes recall. The limit parameter's meaning is 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 (Search) and resource (this week's supermarket/drugstore/liquor-store deals) plus scoping (household's own country and selected chains), which clearly separates it from list/pantry siblings. The return fields are named, so the agent knows exactly what comes back.

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 explicit usage context ('meant for cooking and shopping questions, not for listing every deal') and practical input guidance about using a product word in the household's country language. It does not route to a named alternative sibling, but the inclusion/exclusion guidance is clear and actionable.

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