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

Annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description still adds real behavioral context: the hard eligibility gate that will reject most campaigns, the mandatory confirm flag, and the explicit 'Does not launch or send' non-effect. It stops short of saying deletion is irreversible (the schema's 'deletion backup' note hints otherwise), leaving the recovery profile unstated.

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-loaded with the verb and tightly compressed into three sentences with zero filler. The 'APP:' prefix is vestigial noise and the telegraphic fragment style ('Draft, or cancelled and never launched, with zero sends...') takes a second pass to parse, but nothing is padded.

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?

For a destructive, 9-parameter tool this covers the safety gate and the confirm requirement, and the output schema handles return values. But with two identifier parameters (`id` and `campaignId`) both present and neither explained, an agent cannot reliably know which to supply — a material gap for correct invocation.

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 only 22% across 9 parameters, so the description carries most of the burden — and it explains only `confirm`. It says nothing about the duplicated `id` vs `campaignId` identifiers (a real invocation hazard), `idempotencyKey`, `reason`, or the four external* correlation fields, all of which are undocumented in both places.

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 and resource with scope: 'Deletes an outbound email campaign on sendblox.io only,' then enumerates the eligible states (draft, or cancelled and never launched with zero sends/recipients/jobs/review items). That eligibility list implicitly separates it from cancel_campaign and pause_campaign, but no sibling is named, so differentiation requires inference.

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 gating conditions ('Draft, or cancelled and never launched, with zero sends, no recipients, no scheduled or in-flight jobs, and no review items') are effectively precise when-to-use criteria, plus 'Requires confirm true'. What is missing is explicit routing for the ineligible case — the description never says to use cancel_campaign instead when the campaign has sends or live jobs.

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