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

Annotations already declare readOnlyHint/destructiveHint=false, but the description adds substantial behavioral context: intraday refresh cadence (~10-15 min), the consequence at 100% (campaign exits the auction until midnight), and the auto-discovery scope when campaign_ids is omitted (all ENABLED campaigns of the ad product). This is well beyond the annotation surface.

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 "READ-ONLY, LIVE" and the core fact, then the question it answers, then routing guidance. Slightly dense with several parenthetical asides, but each sentence carries distinct information (cadence, 100% behavior, exclusion, auto-discovery default).

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 6-param, no-output-schema read tool, the description covers scope (intraday vs daily), cadence, the critical 100% threshold behavior, and default discovery behavior. It does not describe the return shape (per-campaign percentage plus the at_risk list implied by threshold_percent), which is the only notable gap.

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 high (83%), so the schema already documents most parameters; the description still adds the default value for ad_product (SP) and the semantics of omitting campaign_ids, which reinforces rather than duplicates the schema. The threshold_percent/at_risk relationship is left to the schema.

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 — how much of each campaign's DAILY budget is consumed today, in percent — and immediately contrasts itself with the sibling data sources (execute_sql for history/ACoS, fact_campaign_daily as daily-only). An agent can distinguish it from every other ads_* tool at a glance.

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 ("quali campagne stanno per restare senza budget adesso") and when-not ("Per storico, ACoS, spesa e trend usa execute_sql, NON questo tool"), plus the exclusivity claim that it is the UNICA fonte of today's data. Routing is unambiguous.

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