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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the DESTRUCTIVE label largely restates structured data. The description does add two pieces of real value beyond annotations: that logs persist after deletion, and that user confirmation is required. It stops short of permissions, failure modes, or what happens to dependent state.

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?

Front-loaded and short, with the risk warning and confirmation requirement placed first, which is the right ordering. The opening "[DESTRUCTIVE] DESTRUCTIVE:" is redundant duplication that wastes the most salient position in the text.

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 2-parameter destructive tool with no output schema, the description covers the essentials: risk level, confirmation workflow, preserved data, and the underlying endpoint. An agent could call this correctly without further information, though id sourcing and post-deletion effects remain unstated.

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%: brandId is thoroughly documented inline, while id is bare but self-evident and echoed as {id} in the endpoint path. The description adds no format, sourcing, or validation hints for the id (e.g., how to obtain it via list_growth_triggers), so it only marginally compensates for the bare 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?

States a concrete verb and resource ("deletes a trigger") and adds a useful side-effect clarification ("its logs stay"). Sibling tools like create_growth_trigger and update_growth_trigger make the family obvious, but the description never explicitly contrasts itself with them (e.g., that deleting is not the same as disabling via update).

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?

Provides one explicit operational rule, "Ask the user before calling," which is genuinely actionable for an agent. However, there is no guidance on when deletion is preferable to update_growth_trigger, or whether get_growth_trigger should be checked first for the id.

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