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

Goes well beyond the annotations: it specifies that approving POSTS REAL CONTENT to each card's accounts, that this is the human-in-the-loop gate, how scheduledAt behaves differently for hosted vs connected accounts, that request_changes requires a reason, and that the reason reaches the influencer's chat. The destructiveHint=true annotation is confirmed with concrete, actionable detail rather than merely repeated.

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?

A single dense paragraph, but front-loaded with the purpose and id source before the safety constraint and the per-mode semantics. Every sentence carries information; only the em-dash nesting of scheduling rules makes it slightly harder to scan.

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, non-idempotent, open-world mutation with no output schema and 40% param coverage, the description covers the critical ground: irreversibility of posting, the human approval prerequisite, scheduling semantics, batch limits, and the fact that results are reported per-draft. Nothing an agent needs to call this safely 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?

With only 40% schema description coverage, the description compensates well: it defines approve/reject/request_changes behavior, the reason requirement for request_changes, the 1-20 draftIds batch limit, and the hosted-vs-connected semantics of scheduledAt. It adds meaning beyond the schema's terse 'ISO-8601 go-live time instead of now', though influencerId itself is only implicitly glossed.

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+resource ('Decide an influencer's review-board drafts') and immediately names the id source (get_influencer_agent → drafts.pending), which no sibling tool shares. An agent can distinguish this from get_influencer, chat_with_influencer, or publish_to_managed_account 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?

Explicit when-to-use and when-not-to-use: only after the user has seen the drafts and explicitly said which to approve, and never on the agent's own judgment. It also spells out the three decision modes and the consequence of each, 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.