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

Annotations already flag destructive=true, openWorld=true, and non-idempotent, but the description adds information they cannot: the effect is atomic all-or-nothing, a single bad post (wrong platform or passed time) blocks the entire batch, and the error response names the offending post. It also warns that approval publishes to real accounts, which calibrates the risk of the destructive hint.

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 (real publishing) and free of filler. The final all-or-nothing sentence is long and chains several instructions together, which slightly hurts scanability, but nothing in it 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 the effect, the atomicity, and the error shape, which is what an agent most needs. It leaves the success response undescribed and says nothing about required permissions or how to recover after a named failure beyond 'fix it or ask the user'.

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 0% schema description coverage, the description carries the full burden and does explain the meaning of both parameters: `task_ids` as individually chosen posts versus `plan_id` as every still-waiting post in a plan, and that either is acceptable. It omits format (UUIDs), the 30-item cap on task_ids, and what happens if both are supplied.

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 ('Approves posts waiting for review') and immediately names the consequence that distinguishes it from siblings: the posts become SCHEDULED and publish to real accounts. That separates it from look-alikes such as list_plan_posts, plan_posts, or publish_draft without the agent opening a 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?

Gives explicit when-to-use ('Only call it when the user has said to approve these posts') and a required pre-step ('before that, list what will go out and when'), plus remediation guidance for the failure path. It stops short of naming the sibling tool (list_plan_posts) for that pre-step, so the routing is implied rather than explicit.

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