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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotency; the description adds context annotations can't convey — that it writes out to Google/Meta ad platforms and requires a user with data-mutation rights plus confirm=true. It stops short of stating irreversibility or what gets changed on the external platform, but the added auth/external-write detail is real value beyond the structured hints.

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 short sentences, front-loaded with what runs and where it writes, followed by the gating prerequisite. Nothing wasted.

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 no explanation, but for a destructive 34-parameter, 0%-documented tool the description is far too thin: it gives no guidance on which parameters select the proposal or which are action-type-specific, leaving an agent likely to mis-populate a live external mutation.

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?

34 parameters at 0% schema description coverage, and the description documents only one (confirm=true). It doesn't explain that action_id/rule_id identify the proposal, which fields are needed for a pause vs. budget action, or what dry_run does — the agent must guess across a very large, undocumented surface.

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: executes a pending pause or budget proposal, and names the two external write targets (Google, Meta). An agent can distinguish it from automate_propose_pause / automate_propose_budget by the 'execute pending' framing, though it doesn't name those siblings explicitly.

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?

Implies the workflow (run a proposal that already exists) and states a hard prerequisite (confirm=true, mutating user), but never explicitly says to call automate_propose_pause or automate_propose_budget first, nor when to use automate_dismiss_action instead. Usage is inferable but not spelled out.

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