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

Annotations declare destructiveHint/openWorldHint but not the mechanics; the description adds real value by disclosing that posts are generated a couple of days before publish, land in the calendar as scheduled editable entries, and consume credits for image posts. It leaves the non-idempotent behavior (what happens on a second start) unstated, which the annotation only flags without explaining.

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 action in a three-word sentence, then consequences. Four short sentences, all carrying information, though the credit sentence and the pre-call instruction could be merged without loss.

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 and only one parameter, the description covers the important unknowns: deferred post generation, calendar placement, editability, and credit spend. It does not state whether the campaign needs a plan or slots first, nor what the call returns, which are moderate gaps.

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?

Single `id` parameter with 100% schema coverage, so the schema fully documents that the campaign is identified by id or name. The description adds no format, lookup or ambiguity guidance beyond that, making 3 the correct baseline.

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?

Specific verb + resource ('Turns a campaign on'), clearly distinct from pause_campaign and delete_campaign. It does not explicitly name or contrast with siblings like plan_campaign or write_campaign_posts, so differentiation is implied rather than stated.

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 a clear precondition for invocation: tell the user the post count and approximate credit cost before calling. It also implies the follow-on path (posts can be read, edited or cancelled later), but names no alternative tool or explicit when-not condition for the start-vs-plan-vs-write decision.

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