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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description goes beyond them by explaining the idempotency mechanism ('a post already waiting just returns its link'), the side effect that the note is shown to the reviewer, and the hard limit that the call cannot itself approve. Those are exactly the behavioral facts an agent needs and that annotations cannot convey.

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 tight sentences, each earning its place: purpose, handoff destination, idempotency, note visibility, and the non-approval boundary. The most important constraints are front-loaded and there is no 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 an output schema present, return values need no explanation; the description instead covers what an output schema cannot — usage context, idempotent re-call behavior, reviewer-facing side effects, and the human-approval boundary. Nothing an agent needs in order to call this correctly is missing.

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 50%: note is documented in the schema, post_id is not. The description partially compensates by characterizing the acceptable post_id values (a draft, or a rejected post you have fixed), but adds nothing about note beyond what the schema already says. This lands at the baseline for partial coverage.

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 — sends a draft or a fixed rejected post for human approval — and explicitly contrasts its role with show_posts/approval_url where the approval actually happens. The closing line 'It does not approve: only a person can' sharply separates it from any sibling that might look like an auto-approve action.

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?

Clearly scopes when to call it: on a draft, or on a rejected post that has been fixed. It also names the downstream surface (show_posts or approval_url) so the agent knows the handoff target. It stops short of naming sibling alternatives to use instead (e.g. create_post, unapprove_post) or explicit when-not-to-call conditions.

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