Jockey Delivery — Same-Day Local & Nationwide AI Commerce

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

Annotations say non-read-only, non-idempotent, non-destructive, open-world. The description adds real behavioral context: it records acceptance, returns a Stripe payment page, and nothing is charged until the shopper pays. It also discloses refusal conditions (expired quote, changed order). Missing explicit mention of idempotency/duplicate-call behavior, so not 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?

Four short sentences, each earning its place: precondition, action/return, payment reassurance, failure handling. All 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?

For a single-param, no-output-schema tool, it covers everything an agent needs: when to call, what it returns, that no money moves yet, and what to do on refusal. Complexity is low and the description matches 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?

Only one parameter, checkout_token, and schema coverage is 100%, so the schema already documents it. The description names related fields (checkout_url, quote_expires_at) but doesn't add syntax or semantics 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 (confirms the checkout, records acceptance) and clearly differentiates from the sibling create_checkout by defining itself as the post-review confirmation step that yields a payment 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?

Explicit preconditions: 'Call only after the shopper has seen and accepted the create_checkout review.' Also gives a fallback path ('then call create_checkout again') when the quote expired or details changed, so the agent knows when this tool is and isn't the right call.

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 declare non-read-only, non-idempotent, non-destructive, open-world, so the description must add the rest. It usefully discloses that nothing is charged here, that price/shelf/delivery are re-checked, and that delivery_option may silently become next-day or be refused — strong behavioral detail. It does not cover auth/permission needs or whether repeated calls create duplicate orders.

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?

Four tightly packed sentences, front-loaded with the primary action, followed by the return payload, the required next step, and the conditional parameter rule. No sentence is redundant.

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?

No output schema exists, yet the description enumerates the review contents (item, address, exact total, delivery window, quote expiry) and the checkout_token, and names the follow-up call. For a 6-parameter mutation tool with an open-world hint, nothing an agent needs to invoke it correctly 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 nonetheless adds real meaning: the variant_id conditional rule and the address semantics reinforce and contextualize what the schema states field-by-field. It stops short of adding format or constraint detail 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 ('Start a real order'), scopes it to one product delivered to the shopper's address, and explicitly differentiates itself from confirm_checkout by naming the two-step flow. An agent can distinguish this from get_product/search_catalog without opening any 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?

Gives explicit ordering guidance: show the shopper the review, then call confirm_checkout with the token if they accept. It also states the conditional prerequisite for variant_id ('when its variant_required is true'), leaving nothing to inference about when this tool applies.

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, so the trailing 'Read-only' adds nothing. The description does add genuine behavioral context by disclosing the scope of the data (service area boundaries, fee, cutoff), but says nothing about freshness of fee/cutoff data or failure behavior for unserved ZIPs.

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 sentence that front-loads the primary content (delivery area) before the secondary details (fee, cutoff, per-ZIP check). No filler or redundancy.

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 carries the burden of describing return values, and it does so adequately by enumerating the four pieces of information returned. It falls just short on edge cases, such as what is returned for an unserved ZIP or whether fees are per-order or per-address.

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% and there is only one optional parameter, so the schema already documents it fully. The description adds only that the ZIP determines whether the area is served, which is a marginal restatement rather than new semantic detail. 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?

Names a specific resource (Jockey Delivery service area, fee, cutoff) and enumerates exactly what the tool returns, including the conditional ZIP lookup. This clearly distinguishes it from checkout and catalog 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?

Usage is implied by the content (an informational lookup for delivery eligibility/pricing), and the optional zip parameter signals a per-ZIP check. However, there is no explicit when-to-use guidance, no statement of when not to call it, and no named alternative.

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=false and destructiveHint=false, so the safety profile is covered. The description adds the useful behavioral fact that the result spans description, images, variants, store offer and delivery facts, which annotations do not convey. It stops short of noting caching, rate limits, or behavior on unknown ids.

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 sentence with no filler: identifiers first, then returned fields, then a one-word safety marker. Nothing can be removed 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?

For a 3-param read tool with full schema coverage and no output schema, the description covers identifiers, lookup origin, and the shape of the returned data. It does not clarify what happens when both url and product_id are omitted, or which of the two identifiers takes precedence, which is a minor remaining 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?

Schema coverage is 100%, so each parameter is already documented in the schema, including the URL format and the ZIP's purpose. The description restates the identifiers but adds no new syntax or semantic detail beyond the schema, which is the baseline-3 situation.

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 the verb (get), the resource (one product), and its two accepted identifiers (product_id or delivery.jockeyvc.com url). Explicitly names its lookup source, search_catalog, which is also a sibling, so an agent can distinguish this detail-fetch from the catalog search.

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?

Names the alternative source (product_id comes 'from search_catalog') and the url form, so the agent knows what inputs are valid. It does not state when NOT to use it or what to do if the product lookup fails, but the when-to-use context is 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, and openWorldHint=false, so safety is covered. The description adds genuine context beyond them: what each result contains (title, brand, price, image, availability, product url) and the store offer, which matters because there is no output 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?

Three tight sentences with the purpose front-loaded and no wasted phrasing. The only near-redundancy is the bare 'Read-only', which restates readOnlyHint=true rather than adding new 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 search tool with no output schema, the description covers purpose, return shape, and the full downstream purchase path. An agent has everything needed to call it and act on the results.

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, zip, and limit are already documented with examples and defaults. The description adds no syntax or format detail beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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 (products) plus a scoping constraint: only what Jockey Delivery can bring from San Antonio stores. That scope distinguishes it from the sibling get_product, which fetches a single known product rather than searching.

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?

Explicitly routes the agent downstream: to buy, use create_checkout then confirm_checkout, and only once the shopper has chosen an item and supplied a delivery address, with the product url as fallback. This names the alternatives and the preconditions that select them.

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