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

Beyond the sparse annotations (readOnlyHint=false, destructiveHint=false), the description discloses significant behavioral consequences: making a private campaign public, turning on per-posted-reply billing (20 credits each), and demanding confirm:true only after user agreement. It also states that future drafts remain held, which is a partial-effect nuance not implied by the annotations or schema.

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?

The description is information-dense yet every sentence carries unique value: purpose, cost, approval-step context, parameter selection, billing warning, and scope comparison. It is front-loaded with the core action and uses clear logical flow from when to use, how to pass parameters, and what to expect. No filler or repetition.

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 tool with one required, three optional parameters and no output schema, the description covers all essential aspects: preconditions, parameter selection, side effects, billing, confirmation, and scope distinction. An agent reading this description has enough information to call the tool correctly and avoid common mistakes. The absence of an output schema is not a gap here because the description's focus is on invocation and side effects.

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?

With schema description coverage at 75%, the schema already explains most parameters. The description adds extra value by clarifying the either/or relationship between post_ids and all:true ('Pass the post_ids the user approved, or all:true.') and by reinforcing the conditional nature of confirm. It does not duplicate campaign_id directly, but the 'campaign created with post_visibility private' context effectively hints at its role. This is a meaningful boost above 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?

The description opens with a specific verb-resource pair: 'Release chosen posts (and their reply drafts) to the community earn feed.' This clearly states the action, the object, and the exact destination. It further differentiates itself from update_campaign by explicitly contrasting scope: 'Unlike update_campaign's visibility flip, this touches only the posts you name and leaves future drafts held.'

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 explicit when-to-use context: 'This is the approval step for a campaign created with post_visibility 'private' (held mode).' It also explains when not to use it and names the alternative: 'Unlike update_campaign's visibility flip...' The confirm:true requirement is tied to the user agreement step, so an agent knows the exact precondition for invocation.

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