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

The description adds substantial unannotated behavior: the ad is created paused, no credits are consumed, nothing spends until go_live_ad_campaign plus human consent, and a repeat call returns the existing campaign rather than creating a second one. That last point sits in mild tension with the supplied idempotentHint=false, though it describes campaign-level deduplication rather than tool-level idempotency, so it is not a hard contradiction. Remaining gaps are account/permission preconditions and where the budget caps come from.

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 with the outcome (becomes a paused Meta ad), then the cost guarantee, then the id-handling. Every clause carries information, though the run-on alternation of run_id/post_id/no-id in one sentence packs three cases together and reads densely.

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?

Output schema exists, so return values need no prose; all parameters are described in the schema; and the description covers the mutation's cost and state implications. For a 4-optional-param ad-creation tool, an agent has everything needed to call it correctly and safely.

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%, so the schema alone documents all four parameters and the baseline is 3. The description earns above baseline by explaining the semantics of the omitted-ids case - it becomes a discovery/listing call rather than an error - and by framing post_id as resolving to the post's run, which the schema only hints at.

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?

Opens with a specific verb and resource: "Boost any post Siren made: it becomes a Meta ad with its own picture or video and caption." It also states the resulting object state ("sent PAUSED"), which distinguishes it from go_live_ad_campaign and make_ads without needing either schema.

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?

Explicitly routes the agent: pass run_id, or a post_id from list_posts, and with neither the tool falls back to listing top-performing posts to choose with the human. It also names the follow-up gate (go_live_ad_campaign plus human approval) and says a previously boosted post returns its existing campaign, so the when and when-not are covered.

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