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

Annotations only establish readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true; the description goes well beyond that by disclosing the default PAUSED state, the real-money spend risk of activating, the currency unit convention, and the dry-run/confirm safety pattern. For a spend-incurring mutation, these are exactly the behavioral facts an agent needs and cannot derive from structured fields.

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 sentences, density front-loaded: action first, then the safety workflow, then the two risk-bearing defaults. Every clause carries operational weight and none is a restatement of the title.

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 an 8-parameter open-world write tool with no output schema, the description covers the create/preview cycle, the spend-risk default, and the budget unit, while the schema handles enum and compliance detail for objective and special_ad_categories. Authentication prerequisites are the only notable omission, and they are not tool-specific.

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 63%, leaving name, ad_account_id and confirm undocumented in the schema; the description compensates for the most important of these by explaining confirm's dry-run semantics, and it restates the real-currency (not cents) convention for daily_budget_major, which is an easy unit error to make. It adds little about objective or special_ad_categories beyond what the schema enums already say.

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 opens with a specific verb+resource ("Create a Meta campaign") and immediately scopes it as a creation tool rather than the sibling mutators meta_set_campaign_status / meta_set_campaign_budget. It never explicitly names those siblings, so its distinctiveness comes from the name alone rather than from the description text.

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?

It gives an explicit two-step protocol: call without confirm to preview, show the preview to the human, then call again with confirm: true. It also states the condition for activating (only when activate is explicitly true) and notes the consequence of getting it wrong (an ACTIVE campaign spends within minutes). This is when-to-use and when-not-to-use guidance with no inference required.

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