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

With no annotations, the description carries the full burden and delivers: it explains that status/budget/flight are read from the advertisements + placements spine rather than a stored display string, so end-of-flight and pacing-completed buys report truth without a rewrite. It also discloses the live-read, staleness-0 snapshot behavior and cursor-based pagination.

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 one-sentence purpose followed by short labeled sections (WHEN TO USE, RETURNS, EXAMPLE). The data-truth paragraph is slightly wordy and partly overlaps the following sentence, but overall every section earns its place.

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 tool with no annotations and no output schema, the description covers return shape (media_buys fields, packages[], status enum), pagination style, and typical call patterns via examples. Minor gaps remain — the nested packages[] contents are only hinted at via the include_snapshot schema description — but nothing an agent needs to invoke it correctly is missing.

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?

The schema already describes pagination, media_buy_ids, status_filter, and include_snapshot; the description adds the AdCP enum framing for status_filter and two example calls showing how to combine status_filter with include_snapshot and how to query by media_buy_ids. This meaningfully compensates for the 60% schema coverage gap.

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: 'List media buys with status, budget, flight and optional delivery snapshots.' The data-truth paragraph and the 'without a full delivery report' clause distinguish it from siblings like get_media_buy_delivery and get_analytics.

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 an explicit 'WHEN TO USE' section with three concrete scenarios: polling open buys, confirming a buy left pending_creatives after sync_creatives, and getting a near-real-time snapshot without a full delivery report. It gives clear context but stops short of naming the alternative tool explicitly.

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