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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description adds substantive context beyond them: the tool returns counts only, never returns e-mails, names or phones, and explicitly cannot build or send campaigns. That is exactly the kind of scope and privacy disclosure an agent needs to avoid misusing the result.

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?

Dense but front-loaded: the audience definition, the sibling-disambiguation rule, the return payload and the read-only scope each appear once in a deliberate order. The enumeration of returned counts is long, though every item maps to a distinct field the agent may need to answer the question, so it is only mildly over-weighted.

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?

There is no output schema, and the description compensates by enumerating the returned counts in detail (total contacts, mailable, unknown consent, unsubscribed, bounced, complaints, 30-day additions, source breakdown, top tags, orders, campaigns by status) plus the exclusion of PII. For a single-optional-parameter summary tool, nothing needed to invoke it correctly 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% and the single optional parameter top_tags is documented in-schema with its default and 0-50 bounds. The description never mentions top_tags, but with full schema coverage the baseline of 3 is appropriate – the remaining gap is only that the description gives no hint of the parameter's role in the tag breakdown.

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 verb+resource (newsletter/e-mail marketing AUDIENCE) and enumerates exactly what it returns: counts of contacts, consented, unsubscribed, bounced, sources, top tags, orders, campaigns. It also explicitly names what it is NOT (CRM leads), so an agent can distinguish it from list_leads without opening a 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?

Gives an explicit routing rule: use this tool (not list_leads) whenever the user asks how many contacts, subscribers, customers or addresses are 'in the base' / 'in the mailing list' / 'for the newsletter'. It also names the alternative destination for the adjacent task (building or sending campaigns happens in the cabinet's Email Marketing section).

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