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

Annotations already establish read-only/idempotent safety, but the description adds real behavioral context beyond them: the call is free and not counted against tasks, ROAS returns 'not applicable' rather than zero on non-revenue objectives, and vague date wording should trigger a clarifying question. This is exactly the kind of quirk disclosure that prevents agent misjudgment.

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 read-only/free banner, then use/no-use guidance, then the return quirk and the ambiguity rule — every sentence carries routing or behavioral weight. The multi-clause KPI enumeration is long but justified by the objective-specific output contract; slightly padding-prone but not wasteful.

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?

With no output schema, the description carries the burden of explaining what comes back, and it does: window-over-window comparison plus per-objective KPI selection, and the 'not applicable' sentinel. Combined with the named alternatives and the date-input rule, an agent has everything needed to call and interpret this 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 description coverage is 100%, so each of the seven parameters is already documented including the date_range exclusivity rule. The description mentions windows and the objective/KPI mapping but adds no syntax or format detail beyond the schema, which matches the baseline 3 for a fully-covered schema.

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 and resource — campaign-level results for a window compared against the prior equal-length window — and enumerates the objective-specific KPIs returned. It also explicitly distinguishes itself from three named siblings (generate_report_now, meta_list_campaigns, meta_analyze_wasted_spend), so an agent can route correctly 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?

It states when to use it ('how Meta is doing', budget reallocation, week-over-week change) and when not to, naming the alternative tool for each exclusion. It even covers the ambiguous-input case, telling the agent to ask for the window rather than guessing.

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