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

Adds substantial behavior beyond the annotations: concrete safety caps (+50% single increase, +100% per 24h window, -80% single cut), the absolute ~5 USD floor and why it exists, the dry-run preview path, and the caveat that sub-floor budgets may stop delivery. Annotations only declare destructive/non-idempotent/not-read-only; the description explains the actual guardrails.

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?

Front-loads the core action and is information-dense, with each paragraph adding a distinct rule or flag. It runs long, and sentences like the instruction to "say plainly that delivery may be thin" read as narrative filler, but nothing is truly 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?

Given a mutation tool with annotations and an output schema, the description covers everything an agent needs: mutation semantics, safety limits, the dry-run path, and the floor exception. No return-value explanation is needed because an output schema exists.

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%, so the description must carry the load, and it does: confirm is defined as a dry-run switch, allow_low_budget is defined as the floor-clearing flag, and daily_amount semantics are explained via the increase caps and floor. customer_id and campaign_id are left implicit, but they are self-evident identifiers.

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: "Sets a campaign's daily budget." This is clear, but it never states which ad platform the tool targets, and sibling tools like update_microsoft_campaign_budget and update_tiktok_campaign_budget occupy similar budget-setting territory. An agent can infer from customer_id/campaign_id that this is the generic/Google Ads path, but the definition does not explicitly differentiate it.

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?

Provides explicit when-to-use and when-not guidance: cuts deeper than -80% should be replaced by pausing the campaign, allow_low_budget=true is the escape hatch for small local campaigns, and confirm=false triggers a dry-run instead of a live change. Alternatives and conditions are named outright.

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