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

Goes well beyond the annotations: it discloses that workflow approval can GO LIVE, that reject cancels the run or returns content to draft, that a missing required note yields a 422, that the approve scope is needed and admin does not include it, and that the tool is agency-plan gated. One tension worth noting: annotations set idempotentHint=false while the description says repeating the same decision is safe (alreadyDecided: true) — this is reconcilable (a different decision still mutates state) rather than a true contradiction, but the description could have said so more precisely.

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 highest-stakes fact (PUBLISHES to social accounts) and dense with zero filler sentences. It is a single heavy paragraph with many parentheticals and mid-sentence mode switches, which costs some scannability, but nothing is redundant.

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, open-world mutation with no output schema, the description covers side effects, permissions, error conditions, idempotency behavior, and the human-confirmation requirement. An agent has everything needed to call it correctly and safely.

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 coverage is 67%, and the description compensates by giving `note` real meaning — it is the reviewer's reason, the submitter is told it, and it is optional unless the org requires one (then 422). It also explains the practical consequence of each `decision` value per approval type, which the bare enum does not convey.

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 ('decide an approval', wrapping POST /api/v2/approvals/{id}) and immediately distinguishes the two modes it governs: 'workflow' approvals (approve resumes a parked run that may publish) versus 'manual' approvals (approve only marks content approved). An agent can tell this apart from siblings like decide_review, decide_approval_group, and publish 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?

Explicitly routes the agent: for manual approvals, nothing posts until you call publish with the contentId, which names the alternative tool and the condition that selects it. It also states the authorization rule (assigned approver or org owner/admin), the required scope, and an explicit 'confirm with the user before approving a workflow approval' guardrail.

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