Locate by description

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior, so the bar is lower. The description adds genuinely useful behavioral context beyond that: results are image-pixel points, and on low confidence it returns up to 3 candidates plus an annotated screenshot, which tells the agent how to interpret ambiguity.

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?

Two dense sentences, no filler, with the primary action front-loaded and the fallback trigger and return behavior following. Every clause earns its place.

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?

Even though an output schema exists (so return values need not be explained), the description still covers the ambiguity path an agent needs to reason about. Combined with annotations covering safety, nothing required to call it correctly 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 description coverage is 100% with only 2 required parameters, so the schema documents both fully and the per-parameter mentions in the description ('described target') add no syntax or format detail. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

States a specific verb+resource ('Find a described target in the current screenshot') and immediately scopes the mechanism ('with a grounding model') and its fallback role ('when refs and marks fail'). An agent can distinguish this from observe and click without opening any schema.

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 an explicit usage condition — invoke when refs and marks fail — which implicitly positions it as the fallback to observe. It does not name the alternative tool by name, so it stops short of a full when/when-not/alternatives statement.

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