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

The description goes well beyond the annotations, which only declare destructiveHint=true. It discloses the refusal behavior when a maintenance log exists, the requirement for confirm to override that refusal, the consequence of losing the maintenance log, and the permanent side-effect that the AST number is never reissued. This is exemplary transparency for a destructive operation, with no contradiction of the annotations.

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 three concise sentences with no filler. The first sentence states the purpose and typical usage. The second explains the refusal and confirm logic. The third states the permanent non-reissuance of the AST number. Every sentence carries necessary information, and the structure is front-loaded with the core action.

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 that this is a destructive tool with a confirm gate and a permanent side-effect, the description covers the essential aspects: when it's allowed, what triggers refusal, what confirm does, and the permanent consequence of the AST number not being reissued. It does not mention permissions or what happens to related records beyond the maintenance log, but that is not critical for invocation. With no output schema, the description doesn't need to explain return values, and the key usage nuances are addressed. It is complete enough for an agent to call 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 coverage is 100% for both parameters, so the schema already describes them. The description adds critical context for the confirm parameter: it explains that confirm must be true to remove an asset with a maintenance log, and that the log is lost. This goes beyond the schema's description of confirm as 'Pass true to remove an asset that carries a maintenance log' by emphasizing the consequence and the refusal behavior. The asset parameter is adequately covered by the schema, so the description's added value is concentrated on confirm.

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 action ('Remove an asset') and the target resource, with explicit conditions for when it's appropriate ('entered by mistake or sold off'). It is clearly distinct from siblings like asset_add, asset_history, and license_* tools, which focus on addition, viewing, or licensing. The verb and resource are unambiguous, and the conditions add precision.

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 context on when to use the tool (mistake or sold off) and implicitly when not to (if a maintenance log exists, unless confirm is true). It does not explicitly name alternatives, but the conditions effectively distinguish it from other asset tools. It lacks explicit exclusions, but the guidance is sufficient for an agent to decide.

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