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

Consistent with annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) and goes well beyond them: it discloses exactly what is written and retained ('writes and keeps our read on the post, once per post version'), that repeat calls return the identical read, and that it never approves, changes or publishes the post. It also points at the response's assistantHint for the next step, so the agent knows the loop is not closed here.

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?

Four sentences, front-loaded with the core action and output shape, then the queue rule, then the write/idempotency behavior, then the sibling routing. Sentence one is heavily parenthetical and dense, but no sentence is filler.

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, the description carries the full burden and meets it: it names the returned post fields (images, caption, per-slide text), the read structure (reasons grounded in visible evidence, at most one fact to confirm, a suggested change), the position counter and assistantHint. An agent could call this correctly and interpret the response without further documentation.

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 100%, so the schema already documents all four parameters and the campaignId-when-postId rule. The description still adds workflow meaning the schema lacks: omitting postId means the *next* post in the dashboard's Review order, and `position` reports how many remain — queue semantics rather than field restatement.

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?

Opens with a specific verb and resource scoped tightly ('Walks the owner through ONE post waiting for their review') and immediately enumerates what comes back: post content, up to three reasons, a fact to confirm, a suggested change. It is unmistakably distinct from get_post (read-only fetch), approve_post and ask_for_changes, which it names as downstream steps.

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 explicit when-to-use routing: omit postId to take the next post in the dashboard's Review order, and the owner's yes goes to approve_post (passing `review`) while a change goes to ask_for_changes (passing `review`). Both alternatives and the conditions that select them are named, leaving nothing to inference.

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