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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial behavior beyond them: ALL-OR-NOTHING semantics, that a single invalid op refuses the whole batch and writes nothing, that all problems are named so the batch can be resent, that ops execute in the order given, and the concurrency hazard with someone editing in the browser. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with the core claim and the op inventory before the rationale; every sentence carries information (collision risk, atomicity, error reporting, link semantics). The half-applied 'fourteen changes' illustration is vivid but slightly longer than needed.

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?

For a 12-variant union schema with no output schema, the description covers the critical contract an agent needs: ordering, atomic validation, error reporting, and one worked op example. It is thin on per-op field guidance (icon, iconColor, sectionSurface, textStyle) and on projectId, which leaves some calling risk unaddressed.

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?

Top-level schema description coverage is 0% (projectId and ops carry no descriptions), so the description must compensate and it only partly does: it explains execution ordering and details the `link` op (key sourced from uichemy_list_links, href semantics identical to uichemy_set_link). It never mentions projectId, the 200-op cap, or how the remaining ten op variants map to the listed edit categories, leaving gaps the schema alone does not fill.

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 opening sentence states a specific verb and resource ('Many edits in ONE write') and then enumerates exactly which edit classes the batch accepts (copy, pictures, videos, text styles, button roles, badge designs, image display, section backgrounds/icons). This lets an agent distinguish it from the ~30 sibling set_* tools it supersedes.

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?

It explicitly routes the agent: 'Prefer this to calling the single tools thirty times,' naming the alternative and giving the reason (each single call is its own revision and risks colliding with a browser editor, leaving a half-applied state). The atomicity note reinforces when this tool is the right choice.

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