preview_variants

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

With no annotations, the description carries the full burden. It usefully discloses that all candidates are rendered from ONE identical bound-data query and that bindings/measures must be shared so numbers cannot drift, which is real behavioral value. However it does not say what happens when the shared-binding constraint is violated (hard error vs. advisory), nor anything about cost, permissions, or how many queries are actually executed.

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 dense sentences, front-loaded with the core action and output, with the invariant rationale attached to the rule it explains. Minor formatting defects ('Compare1..4', 'labelled2x2') mar an otherwise tight structure.

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 description does cover the return value, which matters since no output schema exists, and it explains the core invariant. But for a 10-parameter tool with nested binding objects and zero schema descriptions, essential call-shaping details (labels alignment, reportDir purpose, row limits) are missing, leaving an agent to guess.

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% across 10 parameters, so the description must compensate and largely does not. It references specs, labels and bindings conceptually but gives no meaning for connectionId, theme, width/height, locale, maxRows, or reportDir, and does not explain the labels-to-specs correspondence that the 2x2 layout depends on.

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 and resource ('Compare 1..4 candidate specs'), the shared-data mechanism, and the return artifact (labelled 2x2 PNG plus per-candidate critique). It implies the distinction from single-visual preview tools via the 1..4 candidate framing, but never names preview_visual or diff_visual, so the sibling separation is inferred rather than stated.

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?

'Use this to choose between approaches before committing' gives a clear decision-point context for invocation. It lacks explicit exclusions (e.g. use preview_visual for a single spec, validate_spec to check correctness) and says nothing about prerequisites such as requiring a live connection.

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