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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the '[read]' prefix is redundant rather than additive. The description does usefully disclose that it computes estimates (variables missing, send duration at the mail zone's rate limit), hinting at non-trivial server work, but it never says what happens when neither identifier is supplied or when both are — a real gap given both params default to null.

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?

A single dense sentence, front-loaded with the read scope and the identifier options before the payload details. The nested parenthetical list of statuses is a bit heavy but every clause carries payload information.

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 does the heavy lifting on return values and covers subject, bodies, variables, per-status recipient counts and two estimates — enough for an agent to know what it gets. The remaining hole is the identifier contract (both optional, no stated conflict/absent behavior).

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 carries the burden, and it does name both parameters and frames them as alternatives ('email_campaign_id or email_campaign_uuid') — a relationship the schema cannot express. It stops short of stating precedence when both are provided or the error behavior when both are null.

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 opens with a concrete verb tag and resource ('[read] One campaign') and then enumerates exactly what comes back: subject, bodies, {variables}, recipient counts per status, and two derived estimates. The singular 'One campaign' implicitly separates it from list_email_campaigns, but no sibling is named explicitly.

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 returned payload — an agent can infer this is the detail/analytics view for a single campaign versus the list view. There is no explicit 'use this when…' statement, no mention of list_email_campaigns or list_email_campaign_recipients as alternatives, and no prerequisites.

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