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

Annotations already declare readOnly, idempotent, non-destructive, so the safety bar is covered; the description goes well beyond that by disclosing the required PUSHNOTIF_API_KEY credential, the 0-credit cost, and the aggregation semantics when app_id is omitted. These are operationally relevant facts an agent could not derive from structured fields.

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?

Content is ordered well: purpose, metric scope, usage and exclusions, auth/cost, then return shape, so it is front-loaded with what matters most. The single dense paragraph and the full JSON return sketch could be tightened, but every clause carries useful 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 takes on the burden of describing returns and does so fully (summary totals plus campaign and scheduled_queue item shapes). For a two-parameter read-only tool this covers everything an agent needs to call it and interpret results 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 coverage is 100%, so the parameters are already documented and baseline is 3. The description adds meaning beyond the schema by explaining the consequence of omitting app_id (aggregation across all workspace apps bounded by limit rows), which clarifies intent rather than repeating format details.

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 (retrieve) and specific resources (push campaign delivery metrics and scheduled queue items), enumerating the exact metric fields and the cmp_sch_xxxx ID format. It also explicitly names the siblings it is not (check_billing_and_qris_status, list_subscribers), so an agent can distinguish it without opening another 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 concrete when-to-use cases (audit campaign performance, look up scheduled campaign IDs before editing/canceling) and names the follow-on tool schedule_push_notification. It also states explicit when-not cases with the correct alternatives for QRIS invoices and subscriber device lists, leaving nothing to inference.

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