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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful non-schema context: zero credits debited for own data, auth/account requirement, and that the JSON shape matches the public API and dashboard. It omits anything about row limits or response size, but the cost and auth disclosures are real additions.

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?

The core capability is front-loaded in the first sentence, and cost/auth constraints land before the speculative workflow list. However, the trailing 'nightly Slack digests, attribution stacks, autonomous bid-tuning, etc.' is promotional padding that doesn't help an agent decide or call correctly.

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?

With no output schema, the description carries the return-value burden and does list the key metrics and breakdown dimensions. Cost, auth, and data scope are covered for a read-only tool. Minor gaps remain around result volume/pagination and whether historical days beyond a limit are truncated.

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% — both 'days' (1–365, default 30) and 'ad_id' (ownership constraint, omit for all) are fully documented in the schema. The description's mention of by-placement and by-variant breakdowns describes output dimensions rather than adding meaning to either parameter, 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?

States a specific verb+resource ('Live performance for ads owned by your account') and enumerates exactly what the payload contains: impressions, clicks, CTR, daily trend, by-placement and by-variant breakdown. It also names the underlying REST endpoint and dashboard it mirrors, so an agent knows precisely which resource this covers. No sibling tool touches ad performance, so no differentiation is needed.

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?

It implies usage through example scenarios ('nightly Slack digests, attribution stacks, autonomous bid-tuning') and states the precondition of a free account, but never says when not to use it or which sibling to prefer for related tasks. The agent must infer the fit rather than being routed explicitly.

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