Stovefront

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real value on top: it enumerates the four validation rules applied and explains that the downstream ordering happens elsewhere via customer submit and cook confirmation. Undisclosed is what happens when validation fails (error vs. partial result) and whether the generated link expires.

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 filler: the validation/return behavior is front-loaded, and the 'does not place an order' caveat follows immediately where it prevents the most likely misuse.

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 rightly omitted, and annotations cover the safety profile. Given a two-parameter tool, the remaining gap is failure behavior when a dish fails stock/cutoff checks, which an agent would want before calling.

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 50%: kitchen and dish_id carry descriptions, quantity has only min/max bounds. The description mentions quantities being checked against rules and a single shared pickup time, which adds a little semantic framing, but it doesn't explain the quantity limits, the 20-item cap, or what a valid kitchen identifier looks like beyond the schema. Mid-coverage baseline of 3 fits.

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+resource: validates dishes/quantities against stock, cutoff, quantity rules and shared pickup time, then returns a storefront link with the cart pre-filled. That is precise enough to tell what the tool produces. It never names a sibling (get_menu, get_pickup_windows, search_kitchens), so the differentiation is implicit 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?

The second sentence sets a clear boundary: this does not place an order or take payment, the customer submits on the storefront and the cook confirms. That is an explicit when-not, which keeps the agent from treating it as a checkout tool. What's missing is routing guidance for the alternatives (e.g. call get_menu first to obtain dish_ids, get_pickup_windows for timing), which the schema only hints at.

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/idempotent/non-destructive, so the description's contribution is the added semantics: default behavior excludes sold-out and closed offers, and the order model means orders are requests the cook must confirm rather than confirmed purchases. That last point is genuinely useful behavioral context not present in the annotations. It does not discuss auth requirements or response size/pagination, keeping it below a 5.

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 purpose and then the output contents; nearly every clause carries information. The first sentence is a long run-on enumeration, which slightly hurts scannability but wastes no words.

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 an output schema present, the description needn't restate return shapes, yet it still gives a useful summary of what comes back and clarifies the default availability filtering and the request-based order model. For a read-only, three-parameter tool this is close to complete; only guidance on the week parameter and sibling selection 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 description coverage is 100%, so all three parameters (week, kitchen, include_unavailable) are already documented in the schema, which sets the baseline at 3. The phrase 'can be ordered now' weakly implies the include_unavailable default, but the description never explains the week filter or the kitchen slug/link forms, so it adds little 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?

States a specific verb and resource ('Returns one kitchen's menu') and enumerates the payload precisely: dishes, meal packages, prices, dietary tags, stock, cutoff, pickup/delivery times, quantity rules, required options, payment methods, and order model. That enumeration makes it clearly distinct from siblings like get_pickup_windows or search_kitchens without needing to name 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?

Usage is only implied — the agent can infer this is the lookup to call before build_order_link, but the description never says when to use this versus search_kitchens or get_pickup_windows, nor does it state any preconditions or exclusions. The 'orders are requests the cook confirms' line is contextual, not usage 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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: order cutoff values, the pickup place name, two distinct kitchen modes (scheduled slots vs. weekly pickup with dishes), and the privacy constraint that street addresses are never returned.

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, each doing distinct work: return content, mode-dependent shape, and a data-privacy boundary. The most important information (what is returned and that slots are orderable) is front-loaded 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 an output schema present, the description needn't enumerate return fields, yet it still sketches the payload (cutoff, place name, dishes per slot), which is helpful. An agent has enough to call it correctly; only the relationship to sibling tools in the ordering workflow is unstated.

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 kitchen parameter is well documented with slug and storefront-link examples. The description only refers to 'a kitchen's' times and adds no syntax, format, or validation detail beyond what the schema 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?

The description gives a specific verb and resource: it returns a kitchen's upcoming pickup and delivery slots that are open for ordering, along with cutoff times and pickup place names. This clearly differs from get_menu and build_order_link, but no sibling is named explicitly, so differentiation is left to inference.

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: the caller supplies a kitchen slug and receives orderable slots. There is no explicit statement of when to prefer this over get_menu or build_order_link, no prerequisites, and no exclusions, so the agent must infer the workflow position.

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 and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: only published kitchens, samples and search-hidden kitchens excluded, and a cap of up to 8 matching dishes per kitchen. It does not mention rate limits, ranking order, or cursor behavior, keeping it short of a 5.

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 the core purpose in the first sentence and filtering/exclusions in the second; there is no filler. The long enumeration of return fields is somewhat redundant given that an output schema exists, which costs it the top score.

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 carrying safety and an output schema carrying return shape, the description covers the pieces that matter most: published-only scope, exclusion of hidden/sample kitchens, and the 8-dish cap. Pagination via cursor and result ordering are left unaddressed, but the schema documents the cursor, so nothing critical 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 description coverage is 100% and every filter is documented in-schema, down to the enum list and date format. The description restates which filters exist without adding syntax or edge-case semantics beyond the schema (e.g. how multiple dietary tags combine, or how query terms are weighted), 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 (finds) plus a precisely scoped resource: published Stovefront kitchens and the dishes they have open for ordering. It also states what is excluded (sample storefronts, hidden kitchens), which makes it distinguishable from get_menu, get_pickup_windows and build_order_link without opening the 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 makes the search/filter use case clear (keywords, dietary tags, pickup date, area), so usage is implied. But it never says when to prefer this over the siblings - e.g. that get_menu is the way to see a single kitchen's full menu or get_pickup_windows for timing detail.

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