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

Annotations only declare destructive/openWorld/readOnly=false, but the description adds substantial behavior: a confirm_id preview-then-write flow, read-after-write verification per placement and per id, a hard MAX 25 batch limit, the internal daily_budget → v3 budget{budgetType:DAILY} conversion, and the guarantee that existing audience segments are preserved. This is the kind of operational context annotations cannot express.

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?

Content is largely earned and the subject is front-loaded, but the entire definition is one dense uninterrupted paragraph mixing mode selection, flow, limits, aliases, and exclusions. It is readable but hard to scan, and a few clauses (the alias list) could be tightened.

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 zero-required-parameter, six-parameter mutation tool with nested objects and no output schema, the description covers single vs batch invocation, the confirmation prerequisite, the batch size ceiling, the verification guarantee, and the audience-tool boundary. Nothing an agent needs to call it correctly appears missing.

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?

With only 50% schema coverage and nested objects, the description carries real weight: it documents patches.daily_budget conversion, placement multiplier range 0-900, and placement aliases (top/rest_of_search/product_page/business) that appear nowhere in the schema. It is not fully exhaustive — profile_id and account_id handling are left to the schema — so a 4 rather than a 5.

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 precise verb+resource in Italian ('Aggiorna una o PIÙ campagne SP') and immediately splits the SINGOLA and BATCH modes, so an agent can distinguish this from ads_update_sp_ad_group or ads_update_sb_campaign at a glance. It also names the sibling it is not (ads_update_sp_audience_bidding).

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 explicit when-to-use guidance: BATCH is 'consigliato per agire su più campagne in una volta, es. "sistema 10 campagne"', and the placement flow is spelled out step-by-step (execute_sql → ads_list_sp_campaigns → anteprima → conferma → questo tool). It also states a clear exclusion: audience segments are not touched here, use ads_update_sp_audience_bidding instead.

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