Paddock Cards

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

With destructiveHint and idempotentHint already declared, the description adds real value: it discloses that the service verifies ownership and per-item fulfillment cutoffs, and that it 'returns actual refund state' rather than a canned acknowledgement. It doesn't restate irreversibility explicitly, but the eligibility/cutoff disclosure is the more useful non-obvious trait.

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 sentences, purpose front-loaded, then the pre/post-payment split, then service guarantees and required inputs. Dense but nearly every clause carries information; only the card_ids repetition of the schema is mildly 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?

An output schema exists, so return values needn't be explained, and safety annotations cover the destructive/idempotent profile. The remaining gap is the required expected_revision parameter, whose concurrency semantics are not explained anywhere the agent can see them.

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%: card_ids and order_access_token are already documented in the schema, and the description largely repeats the card_ids guidance. The two undocumented parameters are only partially addressed — order_id and order_access_token are named as required, but expected_revision is only alluded to as 'at its current revision' with no explanation of optimistic-concurrency failure.

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 ('Cancel an eligible purchase') plus the scoping condition ('at its current revision'), and splits behavior by pre-payment vs post-payment state. An agent immediately understands this mutates an existing order, which no sibling (prepare_order, read_order, search_cards) does.

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 conditional usage: omit card_ids before payment for whole cancellation, supply card_ids after payment for partial cancellation. It does not explicitly name alternatives or state when not to use it (e.g. ineligible/non-cancellable orders), so it stops short of full routing 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?

Beyond the annotations, the description discloses critical behavior: no charge or mailing is authorized, returns include previews, exact price sum, payment URL, and order_access_token, and losing an omitted-token response requires a new ID. It also explains idempotent retry behavior and privacy-safe validation errors.

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?

The description is front-loaded with the core action and stays information-dense with little waste. However, it is a single dense paragraph covering many operational details and could be more structurally scannable.

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 complex purchase-preparation tool with an output schema and existing annotations, the description supplies the essential operational context: unpaid state, returned artifacts, token-loss consequences, retry constraints, and validation behavior. Nothing critical for correct invocation appears 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?

With 67% schema description coverage, the description adds useful meaning for top-level parameters: request_id must be caller-generated UUID, order_access_token should be generated and privately stored for recoverable first requests, and the cards array represents a single purchase of 1–500 explicit compositions. It compensates for gaps in request_id and retry 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?

The description states a specific verb and resource: preparing one unpaid purchase of 1–500 cards. It clearly scopes the action as unpaid and non-mailing, which distinguishes it from sibling tools like read_order, cancel_order, and search_cards.

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 gives clear usage context, including caller-generated request_id semantics and retry rules with the same token and unchanged cards. It does not explicitly name alternatives such as read_order or cancel_order or state when to prefer those 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 declare readOnly, idempotent and non-destructive, so the safety profile is covered; the description adds value beyond that by flagging the resource as 'private' (capability-gated) and by disclosing that payment, per-card production and mailing are tracked as distinct states. That state-model note is real context an agent would otherwise have to discover from the output.

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 with the operation and its required inputs, and the state-model caveat placed last. Nothing is wasted.

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-shape explanation is not required, and annotations cover the safety profile; what remains is the state-model hint, which the description supplies. The one gap is that the undocumented order_id parameter is clarified only obliquely via the word 'parent'.

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 only 50% — order_id has no description at all — so the description compensates by calling it the 'parent' order_id, signaling that card-level identifiers are distinct entities under it. The token's secrecy requirement is already documented in the schema, so that part is repetition rather than added value.

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 (read a private purchase plus its order.cards), which no sibling does — cancel_order and prepare_order mutate, search_cards queries a different resource. It stops short of naming any sibling explicitly, so the differentiation is inferred rather than declared.

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 mention of 'using the parent order_id and order_access_token' implies the required credentialing path, but there is no statement of when to reach for this tool versus alternatives, nor any exclusion (e.g., use search_cards to find an order first). Usage is implied, not guided.

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?

The annotations already declare read-only, idempotent, non-destructive behavior. The description adds useful context that public browsing requires no account or key and that results are 'currently available' cards, but it says nothing about pagination behavior despite a cursor parameter, nor about result limits or sorting.

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?

The description is two tight sentences that front-load the core purpose and add one high-value access note. There is no wasted language.

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?

Although an output schema exists and need not be explained, this is a 12-parameter search tool with a cursor and low schema description coverage. The description omits pagination, limit semantics, the text-search parameters, and most filter behavior, leaving significant gaps for an agent invoking it correctly.

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 only 17%, so the description needs to compensate, but it names only five filter dimensions (occasion, tone, format, artist, budget) and the ordinary/artist distinction. It leaves query, humor, kind, limit, cursor, require_printed_text, and printed_text_contains without meaningful added explanation.

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 uses a specific verb ('Find') and resource ('cards') and specifies the scope ('currently available ordinary and artist cards') plus the main filter dimensions. It is clear enough to distinguish this browsing tool from the order-management siblings, though it does not explicitly name any sibling alternative.

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 sentence 'Public browsing needs no account or key' implies the tool is for public browsing and gives an important access condition. However, it does not state when to use this instead of other tools, nor does it describe when not to use it or how it relates to the order siblings.

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