act_sequence

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

With no annotations provided, the description carries the full burden, and it excels. It discloses the return format (JSON with per-step ok/message), the stop_on_error semantics, the step op types and their optional fields, and the landing-point evidence in click messages. It also reveals performance characteristics (measured round-trip times) and the advice about screenshots, giving an agent a realistic mental model of execution and side effects.

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?

The description is long but every sentence earns its place. It front-loads the core value proposition and usage rule, then systematically covers step ops, the screenshot tip, stop_on_error, and return details. The bold and star markers guide attention. For a tool with this many op variants and options, the density is appropriate—no filler, all actionable.

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?

Given the tool's complexity (7 op types with numerous optional fields) and the absence of an output schema, the description covers all critical aspects: op syntax, usage heuristics, error behavior, return structure, and a practical optimization. It even addresses a common failure mode (off-target clicks) and how to verify without extra calls. An agent has everything needed to call it correctly and efficiently.

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%, but the description fully compensates. It enumerates every op (click, type, key, wait, sleep, list_windows, screenshot) with their sub-fields, and explains the stop_on_error parameter's default and effect. This is far richer than the generic 'steps: array of objects' schema, enabling an agent to construct valid step objects without guessing.

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 states a clear purpose: batch-executing a sequence of actions in one call to save round trips. It distinguishes itself from sibling tools (click, type_text, etc.) by framing it as the aggregation tool, and explicitly names the batching criterion. The verb 'execute' and resource 'a string of actions' are concrete, and it even quantifies the benefit (30–70s per round trip vs. sub-second tool call).

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?

It provides explicit, actionable usage criteria: submit consecutive actions whose next step doesn't depend on the previous result, and only split when you need to branch on results. It also gives a specific optimization—placing screenshot as the last step to save a round trip—and explains stop_on_error behavior. This directly tells an agent when to use this tool versus individual sibling calls.

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