cancel_order

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

No annotations are provided, so the description carries the behavioral burden. It discloses the effect (cancelling an order is low-risk and reversible in effect), which is useful, and it states the directness (no token needed). However, it doesn't describe failure modes (e.g., what happens if the order is already filled or cancelled), or the response format. The 'never from memory' warning is a good safety disclosure, but overall it's a moderate disclosure for a mutation operation.

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 compact: three short sentences. The main action is front-loaded ('Cancel ONE specific open order by orderId'), followed by safety context and a source warning. Every sentence adds distinct value — 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?

Given the tool has 2 parameters, no annotations, and no output schema, the description covers the purpose, the restrictive scope, and the source of order_id. It lacks details on what happens on failure (e.g., if the order doesn't exist), and doesn't explain the 'symbol' parameter's role. For a mutation tool with zero annotation support, it covers the essentials but not edge cases. An agent would likely call it correctly for a normal case but might not know how to handle errors.

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 0%, so the description must compensate for the two parameters. It mentions 'order_id' and where it must come from, which adds meaning beyond the schema's bare 'Order Id' title. However, it doesn't explain the 'symbol' parameter — why it's needed and how it relates to the order. Symbol's purpose is implied but never states that the order belongs to that symbol or that symbol is used for validation. Partial compensation leaves a gap on the symbol parameter.

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 clearly states it cancels ONE specific open order by orderId, which is a specific verb+resource. It distinguishes from siblings like prepare_cancel_all_orders and prepare_dual_revoke by explicitly saying 'ONE specific open order' and 'which orders it never applies to' — the restriction to a single identified order differentiates it from bulk cancel tools.

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 provides clear guidance on when to use it: when cancelling a single identified order, and crucially states the order_id must come from get_open_orders or a prior placement, never from memory. It doesn't explicitly name the alternative for cancelling all orders, but the 'single' qualifier implies not for bulk cancellation, and the sibling list shows prepare_cancel_all_orders exists. Clear context is given, but it doesn't explicitly say 'for bulk cancels use prepare_cancel_all_orders'.

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