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

Annotations already declare destructive, idempotent and open-world hints, yet the description still adds real value: API-type campaigns are mirrored to the ad network, the sync is best-effort, network failures surface as warnings while the local change persists. That partial-failure and eventual-consistency behavior is not derivable from the schema or annotations. It stops short of covering permissions, reversibility of pausing, or the shape of the returned warnings.

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?

Two sentences, purpose front-loaded, with the conditional mirroring caveat placed after the main action. The parenthetical is dense but every clause carries operational information; nothing is redundant.

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 two-parameter mutation with no output schema and an open-world hint, the description covers the essential surface: what changes locally and what best-effort external mirroring implies. Gaps remain around permissions and how warnings are delivered to the caller, but nothing critical to invoking 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?

Schema coverage is 50%: 'id' is documented in the schema, and 'status' carries an enum but no description. The phrase 'Start or pause' usefully maps active/paused onto start/pause intent, adding a little meaning beyond the bare enum, but nothing explains what the id must reference. Baseline 3 is appropriate given the split coverage.

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 pair and resource ('Start or pause a campaign'), so an agent immediately knows this is a state toggle on a single campaign, not a general edit. It does not name the sibling it differs from (update_campaign for field edits, set_campaigns_status_bulk for many ids), so differentiation is left implicit.

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 is only implied by 'Start or pause' – the description never says when to prefer this over update_campaign or set_campaigns_status_bulk, and gives no preconditions. An agent can infer the basic case, but the sibling routing decision must be made from the sibling names alone.

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