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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description still adds real context: publishing replaces the current version, and publish_linked_drafts cascades publication to linked Product drafts, which is a non-obvious side effect worth flagging. The idempotency sentence largely restates idempotentHint, though it adds the 'same input' qualifier.

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 tight sentences: action and result first, optional cascade second, retry semantics last. No filler and nothing buried.

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, nested-body mutation with no output schema, the description covers the main effect and cascade but omits failure behavior (what a stale expected_draft_revision produces) and what the response contains. Adequate but leaves real gaps an agent would hit at call time.

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 description coverage is only 33% (only idempotencyKey is documented in-schema), so the description carries extra weight. It does explain publish_linked_drafts meaningfully, but expected_draft_revision and expected_current_version_id — the optimistic-concurrency guards on a destructive mutation — are left entirely unexplained.

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?

The description names a specific verb and resource ('Publishes an ICP draft') and states the outcome ('as the ICP's new current version'), which lets an agent distinguish it from createIcpDraft and updateIcpDraft. It never names those siblings explicitly, so differentiation is inferred from the effect rather than stated.

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?

The description conveys when the cascade option applies ('With publish_linked_drafts, a new ICP's linked Product drafts are published too') and covers retry semantics. It gives no explicit guidance on when to publish versus keep editing a draft via updateIcpDraft, and no preconditions such as required state of the draft.

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