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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is known. The description adds context the annotations cannot: contacts are not suppressed, outreach stops only for that campaign, and there is an optimistic-concurrency revision check with conflict semantics. Missing is what happens on partial failure within a batch of 50.

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, front-loaded with the cap and the operation, followed by scope-of-effect and the retry rule. No filler and no restatement of the name or title.

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 batch mutation with a nested object, 1-50 item limit, no output schema, and 0% schema description coverage, the description covers scope, limit, and concurrency but omits batch atomicity and what the response returns. Those gaps matter for a 50-item destructive call.

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 0%, and the description never mentions 'items' or 'message_id' by name. It does explain the revision contract ('tied to the revision that was read; after a conflict, read it again'), which gives real meaning to expected_revision that the schema's regex pattern alone does not convey. That partially compensates, but the array/batch structure remains undescribed.

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 ('Skips up to 50 drafts held for review') and clarifies the business consequence ('Each contact gets no more outreach from its campaign'). The 'bulk' framing implicitly distinguishes it from the single-item skipMessage sibling, though it never names that sibling explicitly.

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 scopes usage to drafts 'held for review' and gives a concrete retry rule ('after a conflict, read it again before retrying'), which is real guidance. However, it never contrasts with skipMessage or denyMessage/bulkDenyMessages, so an agent must infer when to pick this over the single-record or deny variants.

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