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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is mostly covered. The description adds a genuinely non-derivable fact: it does not 'spend credits', which matters in a mail tool where campaigns consume wallet balance. It stops short of describing result shape, pagination, or any date-range behavior of the returned analytics.

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 short sentences, but the opening 'Campaign analytics.' is pure duplication of the annotation title and earns nothing. The substantive content is front-loaded only after that waste, and the most differentiating fact (no credit spend) sits at the end.

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 saying what comes back, and 'delivery and engagement analytics' gives a usable if coarse sense of the payload. It does not specify metric names, granularity, or time window, which leaves real gaps for a tool whose entire value is the returned dataset.

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?

There is one parameter (path.id) with 0% schema description coverage; the schema only offers the generic label 'Resource ID'. The description's mention of 'a campaign' is the only hint that the id is a campaign identifier, but it gives no format, no source (e.g. from dealmachine_get_mail_campaigns), and no indication of the nested path wrapper.

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 states a specific verb and resource: 'Get delivery and engagement analytics for a campaign.' That is clear and the per-campaign scope narrows it against the account-level siblings, but it never names those siblings (dealmachine_get_mail_analytics_summary, dealmachine_get_mail_analytics_timeseries), so the agent must infer the boundary. The leading fragment 'Campaign analytics.' merely repeats the annotation title.

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?

Usage is only implied by the phrase 'for a campaign' – an agent can deduce this is the per-campaign view rather than the aggregate summary/timeseries. There is no explicit when-to-use statement, no exclusion against the four other campaign-scoped siblings (cost_estimate, properties_estimate, recipients), and no stated preconditions.

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