record_vision_fallback

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

Annotations are absent, so the description carries the burden. It discloses that each entry represents an adapter gap and that this is a report rather than bookkeeping, which is meaningful behavioral context. However, it does not explain whether records accumulate, whether repeated calls create duplicates, or what side effects occur besides recording.

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 sentences with no filler. The first sentence front-loads the action and trigger; the second adds useful semantic framing and a cross-reference to flywheel_stats. Every sentence 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?

The conceptual purpose is clearly explained and an output schema exists, but the lack of parameter documentation and the absence of annotations leave gaps for an agent trying to call this correctly. It is adequate for a simple reporter but not fully self-sufficient.

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%, so the description must compensate, but it only indirectly references field_label as 'a field.' platform, succeeded, and dom_attempts are left undocumented; an agent must infer their meaning from names and default values.

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 specific verb and resource: 'Record that the DOM locator failed and vision had to resolve a field.' It further clarifies the purpose as an 'adapter gap report, not bookkeeping,' which distinguishes it from generic logging or bookkeeping tools and from siblings like record_answer or report_failure.

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 first sentence gives the exact triggering condition for use: DOM locator failure followed by vision resolving the field. The 'not bookkeeping' note and pointer to flywheel_stats().adapter_gaps help frame interpretation, though it does not explicitly name alternative tools or provide when-not-to-use guidance.

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