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 description is not the sole source of the safety profile. It still adds real context beyond them: the operation is an archive rather than an irreversible delete, the result is restorable, and the call is limited to drafts. The final sentence merely restates idempotentHint, which earns no credit but does not hurt.

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 sentences with the core action and its precondition front-loaded, and no wasted framing. The third sentence duplicates the idempotentHint annotation rather than adding information, which is the only real inefficiency.

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 with a nested optional body and no output schema, the description covers purpose, eligibility, reversibility and idempotency well. It leaves the entire body object undocumented, which is the one thing an agent most needs explained before calling this tool.

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 description coverage is 0%, yet the description says nothing about the required params.id or the optional body fields after_message_id and discard_unsent_drafts. The discard_unsent_drafts flag in particular is opaque — an agent cannot tell whether it broadens the discard scope or merely affects unrelated drafts — and the description does not compensate for that gap at all.

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 specific verb and resource ('Discards a draft campaign') and explains the mechanism ('by archiving it'), which distinguishes it from a hard-delete tool and hints at the archiveCampaign sibling. It does not explicitly name which sibling to use instead, so it falls just short of a 5.

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?

'Only drafts can be discarded' gives a hard precondition that tells the agent when the call is valid, and 'a discarded draft can be restored' points toward a restore path. It never names restoreCampaignDrafts or archiveCampaign as the explicit alternatives, so the routing guidance is implied rather than stated.

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