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

Beyond the annotations (which only flag destructiveHint=true), the description discloses the exact scope of destruction (it reverts the prior image and propagates that to the CMS) and the non-obvious two-step confirmation protocol: the first call returns a summary plus a confirmToken, and the call must be repeated with that token to proceed. This is material behavior an agent cannot infer from the annotations or schema.

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?

Three sentences, each carrying distinct payload: what is reverted and where, the eligibility precondition, and the destructive confirmation flow. The destructive warning is front-loaded before the procedural detail.

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 mutation with no output schema, the description covers the safety-relevant mechanics (destructive scope, confirmation handshake, eligibility check) and even sketches the first-call return value. It omits any note on permissions or how to verify the revert landed, a minor gap.

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 67%; confirmToken is already documented in the schema, but the description reinforces its lifecycle (obtained from a prior call, omitted on the first call), and 'the last apply_post_image' clarifies what postId's revert target actually is. The undocumented postId remains self-evident, so this adds meaning without fully compensating for the coverage gap.

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 precise verb and resource ('Puts back the featured image the post had before the last apply_post_image'), explicitly ties itself to the sibling it undoes (apply_post_image), and notes the effect extends to the CMS. An agent can distinguish it from apply_post_image, upload_post_image, and restore_photo_original 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?

Gives an explicit precondition — 'Only possible while get_post_image reports canRevert' — which tells the agent when the call is valid and routes it to the sibling that reports eligibility. It stops short of naming the alternative to use when canRevert is false (e.g. apply_post_image), so it is clear context rather than full when/when-not routing.

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