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

Annotations already declare the write/safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent), so the description adds real value beyond them: the campaign starts PAUSED, budget is in account currency, and an absolute budget cap applies. The dry-run vs apply semantics of confirm are also disclosed. It does not discuss auth/permission needs, but the added behavioral context is substantive.

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?

Four short, front-loaded statements with no filler; each clause (state, type values, budget units, cap, confirm semantics) delivers distinct information. Well structured for 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?

An output schema exists, so return values need not be described. For a create-mutation with annotations, the description covers the operationally critical points (paused start, budget units, confirm gate). Only the account_id vs customer_id distinction and the name param are left to the schema.

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% across 6 params, so the description carries the burden. It documents campaign_type (enumerated values), daily_budget (currency), and confirm (preview/apply), but leaves name, account_id, and customer_id completely unexplained, so it only partially compensates for the schema 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 ('Creates a campaign in Microsoft Advertising') and the platform qualifier cleanly separates it from the many sibling campaign creators (create_meta_campaign, create_linkedin_campaign, create_tiktok_campaign). The PAUSED initial state is an extra precise detail that confirms scope.

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 explains the confirm=false preview / confirm=true apply workflow, which is genuine usage guidance, but it never says when to choose this tool over alternatives like create_pmax_campaign or create_search_campaign, nor any prerequisites (e.g. account must be connected). Usage is implied rather than delimited.

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