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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the description has a lower bar, and it clears it by stating exactly what is destroyed (the draft) and what survives (the live version). That consequence framing is genuinely useful beyond the hints; it lacks only error behavior when a draft is absent.

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?

Three short, front-loaded sentences with no padding, and the outcome statement is well placed. However, the final sentence is not merely redundant but incorrect, which costs more than the brevity gains.

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 one-parameter destructive tool with full schema coverage and annotations carrying the safety profile, the description covers the essential consequence well. The misleading empty-body instruction and the absence of any failure-mode note leave it incomplete enough to trip an agent up.

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% on the single `id` parameter, so the baseline would be 3, but the description's closing instruction "Send {} as the body" contradicts the schema, which marks `id` as required and disallows additional properties. This actively misdirects the agent on parameter usage rather than adding meaning.

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?

Specific verb plus resource ("Discard a flow draft") with an immediate scope qualifier: only the unpublished draft is removed while "the live version stands." That distinguishes it from delete_flow, publish_flow, and update_flow, which all act on the flow itself rather than an unpublished draft.

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 scope statement implies when to use it (you want to throw away unpublished changes without touching production), but no sibling is named and no preconditions are given. It never says what happens if no draft exists, or how this differs from delete_flow in practice, leaving the agent to infer the routing.

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