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

Annotations already establish readOnly=true, destructive=false and openWorld=true, so the safety bar is low. The description contributes real behavior beyond that: the output is an interactive dashboard rather than raw rows, the agent is expected to summarise findings, results are chosen per campaign objective, and monetary values are in account currency. It stops short of noting empty-data or rate-limit behavior, but this is solid added context.

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 metric inventory, followed by two short operational sentences on dashboard form, summarisation and defaults. The metric list is long but each item is information the agent may need to describe results. No filler or marketing language.

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 7 optional parameters, no required fields, no output schema and full schema coverage, the remaining burden on the description is to explain the shape of the result and the agent's follow-up behavior — both are covered (interactive dashboard, summarise findings, account currency, 30-day default). Nothing essential to a correct call is missing.

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% with three enumerated parameters, so the schema already carries the semantics and a 3 is the baseline. The description reinforces the default period ('last 30 days') and clarifies that 'results' is objective-dependent, but adds nothing about detail, folder, account or start/end date interplay beyond what the schema states.

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 names the exact resource (Meta Ads performance) and enumerates the metrics returned — spend, results, cost per result, link clicks, CTR, CPC, purchase value, ROAS, daily trend, per-campaign table. That is far more specific than a restatement of the name. It does not, however, distinguish itself from close siblings like meta_insights_query, meta_breakdown or meta_campaigns, so the agent gets no routing signal from the text alone.

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?

'Shown as an interactive dashboard; summarise the main findings' gives an implied working context, and 'Default: last 30 days' sets a fallback period. But there is no explicit when-to-use versus meta_insights_query (custom metrics), meta_breakdown (segmented cuts) or meta_campaigns (structure), and no when-not-to-use condition. Usage has to be inferred from the sibling name pattern.

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