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

The description discloses that this creates a PENDING proposal and that it does NOT pause until automate_confirm_action – a crucial behavioral fact that separates proposal from execution. It also indicates the two-step workflow, implying the action is reversible/incomplete until confirmed. However, it does not mention idempotency, error behavior, or what happens if dry_run/confirm flags are set, which is relevant for a mutation tool with idempotentHint=false and destructiveHint=false.

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 sentences, front-loaded with the core action and the critical 'does not pause until' constraint. Efficient and focused, though it could be tightened slightly and the parameter sourcing feels a bit list-like. No wasted words, but not maximally tight either.

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 mutation tool with 33 parameters, 0% schema description coverage, and a complex two-step workflow, the description gives only the bare essentials (what it does and the follow-up tool). It omits guidance on the many parameters, error handling, idempotency, and interaction with automate_confirm_action beyond the name. An output schema exists, so return values need not be explained, but the parameter and behavior gap is severe.

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% for 33 parameters, so the description must carry the full burden. It only explains how to obtain campaign_id plus either google_customer_id or meta_ad_account_id. The other 30 parameters (dry_run, confirm, confirm_live, threshold, conditions, rules, dates, etc.) are completely undocumented in both schema and description, leaving an agent to guess their meaning and required vs optional nature (required is 0, so all optional).

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 opens with a specific verb+resource: 'Create a pending pause proposal for a selected Google/Meta campaign.' This distinguishes it from the sibling automate_propose_budget (budget proposal vs pause) and from automate_confirm_action (which executes). An agent can identify this as the proposal step of the pause workflow without opening the 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?

The description provides explicit workflow instructions: it tells the agent where to source campaign_id and customer_id (from google_ads_get_campaigns / meta_ads_get_campaigns) and explicitly names the follow-up tool automate_confirm_action as the step that actually pauses. This is clear when-to-use and what-comes-next guidance, though it does not state when NOT to use this tool (e.g., when a proposal already exists).

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