inkbolt_session_diff_preview

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description goes beyond that with real behavioral facts: outputs use a common sRGB display view, output ICC profiles are recorded but not applied, and fractional grid shifts are rejected rather than resampled. These are exactly the non-obvious constraints an agent needs.

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 sentences, no filler, and the artifact list is front-loaded before the behavioral caveats. It is dense to the point of being slightly packed, but every clause carries information and nothing is repeated from the schema or annotations.

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?

An output schema exists, so return values need no explanation, and annotations carry the safety profile. Given a fairly complex tool with nested focus options and 7 parameters, the description covers the sophisticated semantics (ICC handling, grid-shift rejection, focus modes) well; only the basic session/revision parameters and response_format are left implicit, which is a minor gap.

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 only 29%, so the description does carry weight: it enumerates the focus variants (canvas, region, union-of-items, standalone artboard) and explains the thresholded delta concept. But it says nothing about session_id, from_revision, to_revision, response_format, or the control/timeout parameters, leaving a third of the surface undocumented in both places.

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 names a specific verb (review) and resource (immutable revisions) and enumerates the concrete artifacts produced (aligned before/after PNGs, change mask, RGBA8 deltas, source hashes, structural diffs, coordinate maps). An agent can tell exactly what it gets back. However, it never names or contrasts with the very close sibling inkbolt_session_diff, so differentiation is implied 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?

The description lists capabilities (canvas/region/items/artboard focus) but gives no when-to-use guidance, no conditions that select this over inkbolt_session_diff or inkbolt_session_apply, and no exclusions. A single clause ('session form captures both saved revisions in one transaction') gestures at scope but stops short of routing guidance.

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