check

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: it returns a probability rather than a definitive answer, and there is no output schema to otherwise convey that. Cost/latency caveats for look live only in the schema, so the description is not fully self-sufficient.

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?

Three short sentences: what it does and returns, the verification use case, then the mode switch. Front-loaded with the core capability and zero 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?

With five parameters, one enum, and no output schema, the description covers the essential contract: a probability answer about current on-screen text plus the visual-mode switch. It leaves the source/window/threshold parameters entirely to the schema, which is acceptable at this coverage level but slightly thin for a tool whose accuracy depends on which window is read.

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 80%, so the enum and look semantics are already well documented in the schema. The description's look=true clause largely restates that schema text rather than adding new nuance, and it says nothing about source, window, or threshold. 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 a specific action (ask a yes/no question about on-screen text) and the return type (probability), which is more precise than a generic 'observe'/'check screen'. It never names a sibling tool to contrast with, so the agent must infer that this differs from observe or screenshot rather than being told.

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?

Gives a concrete usage context: verifying whether the previous step succeeded. It also gates a mode (look=true when the subject is the picture itself: in-game, images, colors). It stops short of stating when NOT to use this tool or naming the alternative action tool for those cases.

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