da_verify_pixels

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It transparently explains polling behavior, default timeout and max, interval, error thrown (NOT_FOUND), and the exact semantics of both predicate types (color count and diff threshold). It also mentions optional region clipping, leaving little hidden behavior.

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 dense but well-structured. It front-loads the core blocking behavior, then methodically explains the predicate types, parameters, defaults, and error behavior. Every sentence adds value, and the example cements understanding. No fluff or redundancy.

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 complex verification tool with no annotations and no output schema, the description is remarkably complete. It covers the predicate grammar, all relevant parameters (except displayId), timing behavior, and error handling. The usage example and explicit conditions for success make it sufficient for an agent to invoke the tool correctly.

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?

The description thoroughly explains the key parameters: predicate structure (with required fields, tolerance, minCount, threshold, baseline), region, timeoutMs, and intervalMs. However, displayId is not mentioned in the description, leaving a gap for one of the five parameters. Given the schema offers no descriptions, this omission is a minor but notable issue.

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 states the tool's purpose: 'Block until a pixel-level predicate holds on the next screenshot'. It uses a specific verb ('Block') and resource ('pixel-level predicate'), and distinguishes from siblings like da_wait_for_text by focusing on pixel conditions. The example 'wait until 200+ red pixels appear on the canvas' further clarifies its intent.

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 provides explicit usage guidance: 'Use this to verify visual state after an action'. It gives a concrete example and explains the blocking behavior with timeout. While it doesn't name alternative tools, the sibling list and the pixel-specific framing imply when to choose this over text-based wait tools.

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