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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description confirms read-only while adding the sibling that performs the mutation. Beyond safety, it discloses the internal decision logic (each flag carries a reason, the ROAS vs cost-per-conversion fallback ordering, the age/sample exclusion rule), which the agent could not infer from any structured field.

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 use case, then the return contract, then scope caveats, with zero filler sentences. The middle sentence is a long packed clause enumerating three flag types, which is dense but each clause carries distinct information; a light bullet structure would read faster.

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 exists, so the description carries the return contract and does so: the entities returned, the reason attached to each flag, the totals and spend share, and the separate bucket for young/low-sample ad groups. Combined with the read-only annotation and 100%-covered schema, an agent has everything needed to call and interpret this tool.

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% and both enums are documented in the schema, so the parameter job is already done there. The description's only added detail is the default period ('last 30 days'), which repeats the LAST_30_DAYS default already stated on date_range; it adds nothing about folder/account/language selection. 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?

States a specific verb and resource (find wasted spend in X Ads) and enumerates exactly what qualifies as a flag: zero-conversion spend with sufficient sample, weak ROAS vs the account (falling back to cost per conversion when conversion value isn't tracked), and cost per engagement far above account average. That level of detail separates it cleanly from reporting siblings like x_ads_performance and x_ads_ad_groups.

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 an explicit trigger ('Use this when the user asks where X Ads money is wasted') and routes the adjacent write action to the alternative ('pausing is x_ads_set_status'). It also states what is excluded from flagging (ad groups under 7 days old or with too small a sample are listed apart), so the agent knows the tool's boundary conditions.

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