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

Beyond the readOnly/idempotent annotations, it discloses freshness semantics (updates in real time as Meta webhooks arrive), a conditional output field (recent_errors appears only when sends failed), how those errors are sourced (send-time API errors plus post-send delivery failures, prefixed with Meta error codes), and how to handle the absent case rather than guessing. That is substantive behavior an agent could not infer from structured data.

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-loads the tool's purpose and return shape, then the conditional error behavior, then the operational instruction — a sensible order with no filler. The inline field list and the detailed error-code parenthetical are slightly dense but each carries information an agent needs.

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 work of documenting the return object and the conditional recent_errors field, which is the key completeness need here. The remaining hole is the lone input parameter's provenance, plus no mention of what happens when a campaign has not started sending.

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?

Only one parameter (campaign_id, uuid) exists and schema description coverage is 0%, so the description carries the burden but says nothing about it — no guidance on sourcing the ID from list_campaigns or what happens with an unknown/invalid ID. The name and format are largely self-explanatory, so the gap is moderate rather than severe.

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?

Opens with a specific verb and resource ('Get live delivery stats for a campaign') and enumerates the exact fields returned, so an agent can distinguish it from siblings like list_campaigns or preview_broadcast without opening the schema. The scope ('live' delivery stats) is stated up front.

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?

The description gives conditional handling guidance ('when sends have failed', 'always relay recent_errors when failed > 0') but never says when to reach for this tool versus list_campaigns, preview_broadcast, or send_broadcast. Usage is implied by the phrase 'live delivery stats' rather than stated as a selection rule or exclusion.

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