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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false. The description adds genuine domain behavior beyond that: the AUTO mode forbids manual keywords/targets and requires ads_create_sp_product_targets with auto_match to modulate bids, the placement percentage range (0-900%), and the allowed strategy values. It does not surface that this write is gated behind a confirm_id preview flow, which the schema carries instead.

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?

It is a single dense run-on paragraph that packs purpose, mode branching, follow-up tools, placement syntax and strategy enums into sentence fragments, with Italian/English mixing. Content is mostly load-bearing and front-loaded, but the lack of bullet/line separation for the many enum lists hurts scanability.

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 3-parameter nested write tool with no output schema, the description covers the decisions that matter: which targeting mode, how to format placement bidding, which strategy to choose, and which tools continue the workflow. The remaining gap is the required confirmation step, which an agent must rely on the schema's confirm_id description to discover.

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 67% and the nested fields (dynamic_bidding, placement_bidding items) carry no schema descriptions at all, so the description does real work: it supplies the targeting_type default and behavior, the placement enum values and 0-900% range, the dynamic_bidding.strategy enum, and the meaning of portfolio_id. It leaves name, state, daily_budget and the date fields unexplained, so it does not fully compensate for the 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?

Opens with a specific verb+resource ('Create a SP campaign') and immediately differentiates the two creation modes (AUTO vs MANUAL), which is the key branch point. It also routes the agent to the correct sibling tools for the follow-up work (ads_create_sp_keywords, ads_create_sp_product_targets), so an agent can place it among the many ads_* tools without opening a 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 states when to pick AUTO ('NON aggiungere keyword/target manuali') versus MANUAL ('default; poi attacchi keyword via ... o ASIN via ...'), and names the alternative tools for each path. It omits any mention of the preview/confirm two-step requirement and the account_id prerequisite (both only in the schema), so it falls short of full when/when-not guidance.

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