diff_layer_snapshots

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

No annotations exist, so the description carries the burden, and it does establish this is a non-mutating comparison producing a structured change report rather than an edit. However, it omits important behavior: whether mismatched or stale snapshots are rejected, whether it is read-only, and how 'changed' is determined. An output schema exists, so return formatting is not required here.

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?

A single tight sentence with the action, the inputs, and the result shape front-loaded. Nothing is padded and nothing needs trimming.

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 output schema covers the return value, so the description need not enumerate result fields. But for a two-argument tool with nested, fully undocumented object parameters, the description should at least say where the snapshot objects come from and what constraints they must satisfy; those gaps are unfilled.

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 coverage is 0% and both parameters are opaque 'object' types with no titles or descriptions, so the description must compensate. It only indirectly implies the parameters are layer snapshots and introduces 'by UID', which actually creates ambiguity about whether before/after are snapshot objects, UID strings, or payloads from snapshot_layer_tree.

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 gives a specific verb ('Compare') and resource ('two layer snapshots') and names the output shape (added, removed, changed nodes), so the operation is unambiguous. It does not explicitly point at the sibling that produces snapshots (snapshot_layer_tree) or distinguish itself from list_layers/find_layers, so it falls short of full sibling differentiation.

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?

Usage is only implied: an agent can infer this is the tool for spotting drift between two captured layer-tree states. There is no stated precondition (e.g. both snapshots must come from the same project/layer tree), no mention of the paired snapshot_layer_tree tool, and no guidance on when a plain list_layers call would suffice instead.

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