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

Annotations mark this as destructiveHint=true and openWorldHint=true. The description adds valuable behavioral context: returns the previous value, that spend happens within minutes, and the confirm pattern. It doesn't explicitly state irreversibility or the acknowledge_large_change requirement in detail (though the schema covers the latter), but against annotations this is solid added value.

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, each earning its place and front-loading the core action, the currency semantics, and the safety-critical confirm flow. No waste.

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 a small parameter set and no output schema, the description covers the essential behavior (confirm pattern, currency units, return value, urgency). It leaves some parameter details to the schema but provides enough context for correct invocation. Slightly shy of 5 due to unaddressed campaign_id and confirm semantics.

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 low (25%), so the description must compensate. It adds important semantic meaning for daily_budget_major (value is in real currency, '50' means $50.00/day), which is not in the schema. However, parameters like 'confirm' and 'campaign_id' are not explained in the description. Baseline 3 reflecting partial compensation for the low schema coverage.

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?

Clearly states a specific verb (change) and resource (Meta campaign's daily budget). Sibling meta_set_campaign_status handles status, so the distinction is implied by the 'budget' vs 'status' naming, though the description doesn't explicitly call out the sibling. This is a clear, specific statement of purpose.

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?

Explicitly instructs to call without 'confirm' first to preview current budget and change size, and explains the urgency (spends within minutes) requiring human confirmation. This is strong, actionable when-to-use guidance including a critical exclusion (don't confirm without human review).

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