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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower; the description still adds real context by flagging LIVE data, clarifying that daily_budget is numeric in marketplace currency and that no campaign-level bid exists, and describing the shape of placement_adjustments and audience_adjustments. It does not describe pagination or result limits, which keeps it out of 5 territory.

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 LIVE scope, then fields, then exclusions/alternatives; each clause carries information an agent needs. It is dense but long, and a few field enumerations (e.g., placement keys) could arguably be trimmed, so not a clean 5.

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?

No output schema exists, and the description compensates well by naming the returned fields, what is absent (performance metrics, campaign-level bid), and where to get each missing thing. The one real gap is the undocumented state_filter/profile_id behavior, which leaves a filter-capable list tool partially under-specified.

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 only 33%: account_id is documented in the schema, but profile_id and state_filter have no descriptions. The description makes no attempt to compensate — it never mentions state_filter's accepted values or profile_id's role, so the filter parameter's semantics are left to inference from its name.

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 (live current state of SP campaigns) and enumerates the exact returned fields (name, campaignId, state, targetingType, daily_budget, bidding_strategy, placement_adjustments, audience_adjustments). An agent can distinguish this from ads_list_sb_campaigns/ads_list_sd_campaigns and from the update/create siblings 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?

Explicit when-to-use ('Usa per VERIFICARE prima di agire o per avere nomi/ID') and explicit when-not with named alternatives ('NON ritorna performance: per ACoS/spesa/ROAS/vendite/click usa execute_sql su fact_campaign_daily', and fact_campaign_placement_daily for placement performance). Routing to ads_list_sp_audiences and ads_update_sp_audience_bidding is also given.

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