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

Annotations declare destructiveHint=true and idempotentHint=false, and the description adds real safety workflow detail beyond that: the dry-run default, the inactive default state, and the confirm_live gate for live enablement. It still omits permissions/auth requirements and what happens to unspecified fields on update, which matters for a destructive mutation.

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?

Three short sentences with zero filler, and the most safety-critical information (dry_run default, confirm_live requirement) is front-loaded where an agent will read it first.

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?

An output schema exists, so return values need not be described, but a 33-parameter destructive upsert with zero schema descriptions is not adequately covered by three sentences. An agent cannot determine required inputs, update-vs-create semantics, or what most fields mean.

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 0% across 33 parameters, and the description explains only three of them (dry_run, is_active, confirm_live). Critical fields such as rule_id, scope, condition, operator, roas_threshold, consecutive_days, cooldown_hours, and lookback_days carry no meaning anywhere in the definition.

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?

The description names a specific verb pair ('Create or update') and a specific resource ('a deterministic ROAS pause rule'), which separates it from siblings like automate_upsert_alert_rule and automate_upsert_seo_alert_rule by rule domain. It stops short of naming those siblings explicitly, so differentiation is inferable rather than stated.

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 gives actionable gating guidance: dry_run defaults to true, is_active defaults to false, and going live requires confirm_live=true. However, it never says when to use this tool versus alternatives such as automate_propose_pause or automate_propose_budget, nor what the upsert key is when updating an existing rule.

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