Diff installed labsUI items

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

Adds substantial context beyond the readOnly/openWorld annotations: it explains the return is a unified patch per changed file, defines the diff direction ("from the registry file to the project file; + lines exist only in the project"), notes that matching items are omitted, and says what happens on no differences. It also states the init prerequisite.

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?

Four short sentences, each doing distinct work: what it compares, what it emits, how to read the output, and when to use it. Front-loaded with the core comparison and no filler.

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?

With no output schema, the description compensates by describing the return format and direction explicitly, and it covers the prerequisite. An agent has everything needed to call this and interpret the result.

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 100% with a single documented `names` parameter including pattern, maxItems, and the empty-array behavior, so the schema carries the burden. The description says nothing about the parameter, so the baseline 3 applies.

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 installed labsUI items with this labsUI version") and pins down the output direction. It is clearly distinguishable from siblings like `update`, `view`, and `search`, which do not produce a patch.

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 it to see local edits before update" gives a concrete situation and implicitly positions `update` as the follow-up action, and "Needs init" flags the prerequisite. It stops short of explicitly naming an alternative for the case where you want to inspect a single item rather than a diff (e.g. `view`).

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