delete_asset

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

With no annotations, the description carries the full burden and does so well: it discloses that the tool mutates Officer control-plane config, is protected and disabled by default, that force is unconditionally refused for agents, and that a forced delete would cascade through balances, orders, trades, adjustments, barriers and referencing market-data/trading instruments. It also names the two concrete error signals, has_dependents and loosening_refused.

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 purpose is front-loaded in three words, but the remainder is a pair of long, hard-to-parse clauses ("The delete is refused with loosening_refused while a rate-limit or order-size barrier references the asset or a Spot Funds P&L bound is denominated in it"). The content earns its place but the packaging makes conditions difficult to extract.

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 destructive mutation tool with no annotations, the description covers cascade semantics, refusal reasons and the protection/disabled state, and an output schema exists so return values need no explanation. What is thin is the authorization model and the recovery path after a refusal (e.g. remove dependents first), which would round it out.

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 does explain what force would destroy, but that content is already fully duplicated in the force property's schema description, so it adds little beyond structured data; the asset parameter's meaning (asset code) 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?

"Delete an asset" gives a specific verb and resource that is unambiguously distinct from siblings such as update_asset, create_asset or delete_trading_instrument. The scope of the operation is further sharpened by naming the two refusal outcomes, but the description never explicitly contrasts itself with those 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?

The description spends its words on refusal conditions (has_dependents, loosening_refused), which implicitly tells the agent when this call will fail, and it warns that force is always refused for an agent. However, there is no explicit when-to-use framing, no prerequisites (permissions, enabled state) and no pointer to an alternative tool for the dependent-row case.

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