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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds real context beyond that: revision checking (optimistic concurrency against expectedRevision), dryRun defaulting to true so the operation is a preview unless explicitly committed, and 'preserves the other shots' scoping the blast radius. It stops short of saying what happens on a revision mismatch (error vs. merge).

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 short clauses, all front-loaded: the action, the precondition, the concurrency/dryRun behavior, the scope guarantee. No filler and no restatement of the tool name.

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 the description covers the key safety behavior for a destructive mutation. However, for a 7-required-parameter nested-object tool with 14% schema coverage, the absence of crop coordinate semantics and idempotency-key guidance leaves real gaps an agent must guess at.

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 14% – only projectId is documented ('UUID string'), and the crop object's x/y/width/height have no textual explanation of whether they are normalized fractions or pixels. The description clarifies expectedRevision ('revision checked') and dryRun ('previews by default'), but leaves itemId, workspaceId, and idempotencyKey semantics unaddressed despite all seven being required.

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 ('Adjust the crop of one existing source view') plus a precondition ('after a layout has been applied'). No sibling performs crop adjustment, so the agent can distinguish it silently, but no sibling is named for contrast.

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?

'After a layout has been applied' gives a precondition, and 'dryRun previews by default' hints at the safe usage path, so usage is implied rather than spelled out. There is no statement of when not to use this versus siblings like editor_composition_edit or timeline_trim_apply, and no guidance on promoting a dryRun preview to a real write.

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