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

Annotations already flag destructive/openWorld, but the description adds the crucial substance: approving publishes REAL posts to live accounts, reject also vetoes approved-but-unpublished scheduled drafts, and reason feeds learning. These side-effect details go well beyond the annotation flags.

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?

The critical consequence (APPROVING PUBLISHES) is front-loaded in caps, followed by the gating rule and edge cases. Dense but every sentence carries non-redundant information.

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 publish gate with no output schema, the description covers the side effects, the required human authorization, the reject semantics, and the scheduledAt constraint. Nothing needed to invoke it 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?

With only 40% schema coverage, the description compensates well: it explains decision semantics (reject teaches via reason), the scheduledAt ISO-8601 override and its single-draftId constraint, and the single-draft restriction. Only influencerId is left unexplained, a minor gap for an obvious scoping id.

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 pair (approve/reject) and the exact resource (an influencer agent's proposed content drafts). An agent can distinguish this from siblings like get_influencer_agent 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?

Explicitly names the prerequisite (user has seen the drafts via get_influencer_agent and said which to approve), the prohibition (never bulk-approve on your own judgment), and the human-in-the-loop gating condition. When-to-use, when-not-to-use, and the alternative read tool are all present.

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