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

Annotations already cover the safety profile, yet the description adds substantial undisclosed context: Slack/webhook URLs are named but never returned, triggerRetired=true means the rule can never fire even while enabled, and each run status is spelled out (fired, skipped_cooldown, skipped_budget, awaiting_approval, in_progress, done, dismissed, error). These are non-obvious semantics an agent could not infer from annotations.

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?

Resource and its parent location are front-loaded, and the final sentence carries the read-only framing and alternative. The main sentence is a long chain of parentheticals that takes effort to parse, but nearly every clause carries distinct information rather than filler.

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?

There is no output schema, so the description must describe the return payload itself — and it does, covering trigger fields, action destinations, scope, enabled/retired semantics, fire counts, recent runs with status values, and the plan's active-automation limit. Nothing an agent needs to interpret the response 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?

Schema coverage is 100% with two documented optional parameters, so the schema carries the burden. The description gestures at scope ('one client or all') which loosely maps to clientId, but it never mentions runsPerAutomation or the per-automation run cap that governs the response size. Baseline 3 is appropriate.

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?

Names the specific resource (the workspace's Automations under AI Visibility → Automations) and enumerates exactly what each record contains: trigger, actions, scope, enabled/retired state, fire counts, recent runs. The verb 'list' is only implied by the name rather than stated, but the returned shape leaves no ambiguity, and the closing pointer to list_pending_approvals separates it from the nearest sibling.

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 declares read-only use and routes a distinct case away: 'drafts waiting on a person are in list_pending_approvals.' That is a real alternative with a stated selection condition. It stops short of telling the agent when to prefer this over get_signals or when the tool is unnecessary, so no full when/when-not matrix.

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