compare_previews

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

Annotations already indicate a read-only, non-destructive operation. The description adds useful behavioral context: the output is a JPEG, it is side-by-side, it uses a shared stretch, and it supports comparing against a checkpoint file. No contradiction with annotations exists.

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?

Single concise sentence with the core purpose front-loaded and no filler. It earns its place by specifying output format, input scope, comparison style, and intended use.

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 tool has 9 parameters and no output schema, yet the description only covers the high-level purpose. Important invocation details such as how id_b and path_b interact, what labels mean, what max_edge controls, and how linked behaves are absent, making it incomplete for an agent to reliably call the tool.

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 low at 22%, so the description must compensate, but it only vaguely explains id_a/id_b as views and stretch as 'same stretch'. Parameters like linked, max_edge, label_a, and label_b receive no meaningful explanation, leaving significant ambiguity for correct invocation.

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 a specific function: producing a side-by-side JPEG comparison of two views or a view and a checkpoint file. The 'same stretch' and 'before/after checks' details differentiate it from single-view preview tools like render_preview.

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 explicitly frames the tool as for before/after checks, which is a clear usage context. It does not name an alternative tool for single-view rendering, but the two-view/checkpoint comparison scope makes the intended use clear.

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