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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description still adds genuine value beyond them: cancellation is irreversible, it is blocked after publication, and the response reports the new media_buy_status and revision. It does not disclose what happens to per-package state or whether partial package updates are transactional.

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 definition is compact and front-loaded: the verb and the mutating fields lead, the irreversible cancellation caveat and return values follow. The shorthand constructions ('paused true/false', 'canceled true') are dense but readable; little is wasted, though slight expansion would aid scanning.

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 12-parameter, nested, destructive tool with no output schema, the description covers the top-level mutations, a critical precondition, and the return fields — enough to attempt the common call. The complete absence of the packages array and the two required parameters leaves a meaningful gap for anything beyond a whole-order pause/cancel/amend.

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%, so the description must carry the burden, and it only explains 6 of 12 parameters. It says nothing about the required media_buy_id and idempotency_key, nothing about the 'account' object, and — most importantly — nothing about the 'packages' array with its per-package paused/canceled/budget/creative_assignments fields, nor about 'revision' or 'cancellation_reason'.

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 verb and resource ('AdCP update_media_buy') and enumerates exactly which fields it mutates (paused, canceled, name, start_time, end_time, total_budget). An agent can tell this is a mutation tool rather than a read tool like get_media_buys, though it never names a sibling alternative explicitly.

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?

Usage context is clear: paused for pause/resume, canceled for cancellation, and the other fields to amend. It also gives a real exclusion — cancellation is not possible once the article is published — which prevents a doomed call. It stops short of routing the agent to alternatives or stating preconditions such as required account/revision matching.

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