send_actions

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

Describes side effects (all actions execute on remote desktop), fail-fast behavior, and default observe_after behavior. Annotations include destructiveHint and openWorldHint, but the description adds meaningful context beyond those without contradiction.

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 well-structured, starting with the core purpose, then side effects, then usage guidelines. Every sentence adds value with no filler, and it's appropriately sized for the complexity of the tool.

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 (multi-step actions, side effects, defaults), the description covers all necessary aspects: purpose, usage boundaries, side effects, and guidance on alternatives. No return value explanation needed as no output schema is present.

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% so parameters are already documented, but the description adds useful semantic detail about defaults (observe_after defaults true) and conditional behavior (observe_image for JPEG). This goes beyond mere schema repetition.

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 clearly identifies the tool as a multi-step action batcher supporting 1-10 predictable UI actions, lists supported action types, and explicitly distinguishes from single-action sibling tools (e.g., 'Prefer this over chaining solo click/type/keys tools').

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?

Provides explicit guidance on when to use (batch predictable actions) and when not to ('Do not batch across unpredictable waits...'), along with a clear alternative (single-step those). This directly helps the agent select the correct tool.

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