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

Annotations already declare readOnlyHint/destructiveHint, and the description reinforces that while adding real behavioral detail beyond them: consolidated/pixel do not run their own image analysis, lens=dom degrades to a structured error when artefacts are absent, and no local filesystem is required. Failure and degradation modes are disclosed, which is exactly the added value the annotation does not 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 action and lens list, then layers consequences. Dense but every clause carries information; losses come only from mild repetition of the lens behavior in two sentences.

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 must describe returns, and it does: mismatch %, verdict, labelled asset URLs, and the DOM byte delta for lens=dom. Combined with the error-degradation note, an agent has enough to call it correctly; only the exact error/response shape remains unspecified.

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 100%, so the schema already documents all three parameters including the inline size limits, so the baseline is 3. The description mostly restates the lens semantics already present in the schema and adds no new format or syntax guidance for comparison_id or include_assets.

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 (Analyze) and resource (one SmartUI comparison) with an explicit scope limiter (one, not many), and names the three lens modes. It is clearly distinguishable from the sibling smartui_comparison_query, whose output feeds the required comparison_id.

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?

Explains when each lens matters (dom gives a real byte delta and needs served artefacts; consolidated/pixel merely surface upstream numbers) and gives an actionable condition for include_assets=inline ('when you cannot fetch URLs'). It stops short of stating when to prefer this tool over smartui_comparison_query.

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