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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds substantial context beyond them: the mandatory preview-then-apply gate, explicit user confirmation before applying, reporting of affected and skipped rules, the pick-a-step skip behavior when switching on, and the blast-radius warning that shared pipeline rules change for every job on that pipeline. That is exactly the behavioral disclosure a destructive bulk operation needs.

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?

Every sentence is an instruction with no filler, and the workflow order is front-loaded. It is dense — five imperative sentences in a single undifferentiated block — but nothing could be cut without losing operational meaning.

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 6-parameter bulk tool with a nested filter object, no parameter descriptions and no output schema, the description covers the critical safety workflow and the preview return contents (affected/skipped rules). It falls short on filter semantics and the request_id/idempotency_key parameters that an agent would need for correct retry behavior.

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%, so the description carries the burden. It explains mode (preview vs apply), rule_ids (exact ids from preview) and implies action ('switch on, off or delete'), but says nothing about the filter's fields, request_id, idempotency_key, or the 500-item cap on rule_ids.

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 the specific verb set (switch on, off, delete) and the resource (automation rules in bulk), so an agent can tell it apart from single-rule siblings like yardstick_automation_rules_update or yardstick_automation_rules_delete. It never explicitly names those siblings, so the differentiation is inferential 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?

Strong procedural guidance: 'First use mode=preview with rule_ids or filter', 'Then use mode=apply with only the exact rule_ids returned by preview; never reapply the filter' — a clear when-to-do-what sequence with an explicit prohibition. It does not compare against alternative tools (e.g. single-rule update/delete) for cases where bulk is unnecessary.

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