vision_reconstruct

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

No annotations are provided, so the description carries the full burden. It discloses the model self-check loop, but says nothing about cost/latency of vision model inference, whether files are written to disk (render implies a side effect), or what happens when iterations run out. For an unannotated tool with a rendering step, this is thin.

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?

One front-loaded sentence with no filler; the purpose and output formats come first. It is efficient, though arguably terse for a nine-parameter tool, so it is not a model of expressive economy.

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?

Nine parameters, zero required, no output schema, and no annotations — the definition should at least clarify that exactly one of image_url/image_path/image_base64 must be supplied, and what a successful result looks like. Defaults for render/iterations are deferred to config variables without explanation. The single sentence is not enough to call this correctly without opening the schema.

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 89%, so the schema already documents model, render, iterations, mime_type, image sources, and reference_layout. The description adds no parameter-level meaning beyond the format list that is already an enum in the schema. Baseline 3 applies when the schema does the work.

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 concrete verb+resource+output: 'Reconstruct a screenshot into code (html/react/svg) with a model self-check.' The output formats distinguish it from siblings like vision_ocr and vision_layout, which produce text or layout instead of code. It stops short of naming an alternative explicitly, so it is clear but not fully differentiated.

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?

There is no statement of when to reach for this tool versus vision_layout, vision_ocr, or vision_compare, which is the most likely confusion given the sibling set. The only hints are 'screenshot into code' and the optional reference_layout parameter, leaving the routing decision to inference.

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