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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's job is scope disclosure — and it delivers: 'One call audits the account' promises a single-call fan-out across four analysis categories and notes results come pre-ranked. It omits any mention of latency, cost, or data-volume caveats for large accounts, which is the only remaining gap.

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?

Two sentences, zero filler: the trigger conditions come first, then the audit contents and return shape. Every clause carries information an agent would otherwise have to infer.

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, three-parameter analysis tool with a fully documented schema and no output schema, the description covers purpose, scope of analysis, and return characteristics ('wasted spend already ranked'). Only minor gaps remain, such as how much data history is needed for meaningful results.

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 100% with per-parameter descriptions and an enum for period, so the schema carries full semantics. The description adds nothing about period defaults or the login_customer_id manager-account case, which is the correct baseline-3 outcome when the schema does the work.

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 concrete verb+resource ('find wasted spend') and enumerates exactly what the audit covers: search terms, keywords and campaigns spending above average CPA without conversions, missing conversion tracking, and disapproved/limited ads. This lets an agent distinguish it from raw-query siblings like run_gaql_query or search_terms without opening any 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?

Opens with explicit trigger phrases ('where money is wasted', 'what to cut', 'why costs are high', 'how to optimize an account') and the imperative 'Start here', which is clear routing guidance. It implicitly positions itself against run_gaql_query ('no GAQL needed') but never states a when-not condition or names an alternative explicitly.

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