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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral detail beyond that: it discloses the internal ordering (conversion tracking checked first, which implicitly flags the accuracy caveat when tracking is broken) and what the tool emits. It does not mention cost, latency, or how the look-back interacts with data freshness.

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 outcome ('where money is going with nothing to show for it'), then a compact colon-delimited list of checks, then the output/handoff. Dense but every clause earns its place; only the parenthetical examples could be trimmed.

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 read-only diagnostic with no output schema, the description does the necessary work of describing what comes back (suggested negative keywords) and where it flows next. A three-parameter, fully documented schema keeps the remaining needs modest, so this is nearly complete.

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 description coverage is 100%, so days, campaign_id, and customer_id are already fully documented in the schema, including the 'ending yesterday' window semantics. The description adds no parameter-level meaning (e.g., how campaign_id scoping changes which checks run), so the baseline 3 applies.

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 concrete verb+resource ('Diagnoses where money is going with nothing to show for it') and enumerates the exact checks it performs (conversion tracking, high-cost zero-conversion search terms, low-intent patterns, keywords to review). That is much more specific than a tautology, though it never explicitly contrasts itself with the data-retrieval siblings like run_gaql or account_overview.

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?

The handoff line ('suggested negative keywords ready to pass to propose_changes') gives useful workflow context and implies the tool is a pre-audit step. However there is no explicit when-to-use/when-not statement and no mention of alternatives for users who want raw query access.

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