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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that only currently ACTIVE campaigns are counted, that paused campaigns silently drop out of both spend and totals, the workaround for getting the true monthly total, that the current partial day is included, that shared budgets are counted once per campaign, and that projection is linear. These are exactly the caveats an agent needs to avoid misreporting numbers.

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-loaded with the purpose, and nearly every clause carries operational information (definitions of expected, projection method, active-only caveat). It is dense and somewhat run-on, mixing Meta routing instructions into a Google Ads tool, which makes it harder to parse than a cleaner bulleted structure would be, but little is 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 formatting needn't be described. The description covers the calculation definitions, the data-completeness caveat, the cross-platform escape hatches, and the optional parameter — everything needed to call and interpret this tool correctly.

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 burden — and it does, explaining that workspace is the customer workspace slug and that it may be omitted when only one workspace exists. That is the key semantic the bare schema lacks; only the accepted slug format is left implicit.

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 deliverable (budget pacing for the current month), the exact comparison it produces (spend vs. expected spend per campaign and in total, plus end-of-month projection), and the platform scope (Google Ads only). An agent can tell this apart from raw performance tools like ads_campaign_performance without opening any 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?

Explicitly scopes usage to Google Ads and routes Meta users to concrete alternatives (meta_list_campaigns/meta_list_adsets for budgets, meta_campaign_performance with daily=True or totals_only=True for spend). It also warns that paused campaigns are excluded and points to ads_campaign_performance for full monthly totals. The only gap is that it never contrasts itself with the sibling ads_budget_status, which an agent could easily confuse it with.

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