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

Annotations already declare destructive=true and idempotent=true, but the description adds context the annotations cannot carry: the consent scopes each action consumes, the fact that some actions spend workspace credits, and the dependency on pre-existing sample approval in Publinio. The instruction to reuse the idempotency key reinforces the retry contract beyond the bare idempotentHint flag.

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 core verbs and constrained to four dense sentences, each carrying distinct information (purpose, consents/credits, prerequisites, exclusion, idempotency). It is efficient, though the compressed phrasing around 'existing sample approval in Publinio' and the trailing idempotency note make it slightly terser than ideal.

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, consensual mutation with an output schema, the description covers consents, credit side effects, prerequisites, and an explicit negative constraint, so the agent has what it needs to call safely. It omits what a revision mismatch returns and the meaning of brandId/automationId, minor gaps given the output schema and destructive annotation carry the rest.

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 0%, so the description must carry the load. It maps the five verbs to the action enum and clarifies revision as the 'expected revision' (implying optimistic-concurrency matching) and the idempotency key's reuse semantics, but brandId and automationId are never explained. Two of five required parameters remain undefined in both schema and description.

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 names the exact verbs (pause, archive, activate, resume, sample) and the resource (automation), and it differentiates from siblings by explicitly ruling out sample approval, which routes an agent to approve_automation_sample rather than this tool. An agent can select this over prepare_automation, update_automation, or set_automation_delivery without opening any 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?

It states prerequisites conditionally per action (activate/resume/sample require automations:run consent; auto delivery requires posts:schedule consent plus prior sample approval), and gives an explicit exclusion ('Never approve a sample through this tool'). This is when-to-use, when-not-to-use, and the required conditions all at once.

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