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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds genuinely new behavior: the campaign remains PAUSED on the provider after this call, and it is human-approved only, never auto-approved. The 'spend' tag hints at cost exposure but does not spell out what happens to budget or partial state if the retry fails again.

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 tight sentences, front-loaded with classification tags then the action and its constraint. Every clause contributes: identifier options, retry-from-failure semantics, paused-state outcome, and approval requirement.

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 destructive, open-world mutation with no output schema, the description covers the critical agent-facing facts: approval gate, resumed-from-failure semantics, and post-call state. It lacks detail on failure modes, cost implications, and what is returned, which keeps it short of full completeness.

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 coverage is 0% and both parameters are bare nullable anyOf fields, so the description must carry meaning. It names both identifiers and signals they are alternatives ('ads_campaign_id or ads_campaign_uuid'), but does not state precedence if both are supplied, formats, or whether at least one is effectively required despite the schema marking none as required.

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 gives a specific verb ('Retry building a campaign') plus the resource and the exact recovery condition ('from the step that failed'), and it clarifies the outcome state ('still PAUSED there'). That separates it in spirit from create_ads_campaign and activate_ads_campaign, though neither sibling is named 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?

It implies the right occasion — a previously failed build step — and states the human-approval precondition. However, it never says when to prefer activate_ads_campaign or create_ads_campaign instead, so the agent must infer the routing among the three campaign-state tools.

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