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

Annotations already establish readOnly/openWorld=false/destructive=false, so safety is covered. The description adds genuinely non-structured behavior: it returns live bid+state values, it deliberately omits performance metrics, and — most valuably — it defines what an empty result means and instructs the agent not to fabricate keywords.

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 core identity ('LIVE: ... BID e stato ATTUALI'), followed by usage, exclusion, and edge-case handling in tight sequence. Slightly dense but each sentence carries distinct information.

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, so the description usefully covers the return shape (current bid/state, not performance) and the empty-result semantics. What remains unaddressed, pagination behavior and the meaning of state_filter, are minor for a read-only list tool whose safety profile is already given by annotations.

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 20%, so the description must compensate and does so only partially: it names campaign_id and ad_group_id as filters, but leaves state_filter and profile_id unexplained. account_id is documented in the schema itself. With the two primary filters covered, baseline-adequate but incomplete.

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 ('keyword Sponsored Brands con BID e stato ATTUALI') and immediately frames it as the pre-rebid read. Explicitly distinguishes itself from the alternative (execute_sql for performance), so an agent can route correctly without opening the 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?

Names both when to use ('la lettura da fare prima di riofferire su SB') and when not to ('NON ritorna performance: per spesa/vendite/ACoS usa execute_sql su fact_keyword_daily'), and gives the exact filtering conditions (campaign_id/ad_group_id). Nothing is left to inference.

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