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

The annotations already declare readOnly, idempotent, and non-destructive hints. The description adds important context beyond annotations: the pixel-diff functionality is disabled on the remote endpoint, which changes tool behavior depending on endpoint, and it explains why (unbounded image decode). It also clarifies that passing a description makes the call stateless, which is useful operational knowledge. No contradiction with annotations.

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?

The description is compact—four sentences that front-load the core action and outputs, then a contextual warning and a clear alternate usage mode. There is no filler; every sentence contributes. It is well structured and immediately understandable.

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?

Given a six-parameter all-optional tool with no output schema, the description covers the essential behavior: it tells what the tool returns, how to invoke it statelessly, and the main caveat about the remote endpoint. The schema describes each parameter individually, so the description covers the high-level contexts. It does not fully address what happens when both screenshot and description are provided, but this is a minor ambiguity given that the description explicitly directs to omit screenshots for the description mode.

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?

With full schema coverage (100%), the baseline is 3. The description compensates by explaining a key relationship among parameters: 'Omit before_screenshot/after_screenshot and pass a description to evaluate the design against UX principles statelessly.' It also directly refers to the primary parameter (description) and its role. This adds a usage constraint not present in the schema's individual parameter descriptions, raising the value.

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 states a specific verb and resource: 'Evaluate a design description against UX principles' and details the outputs (relevant principles, violations, suggestions). It clearly distinguishes from kindred 'audit_*' and 'get_*' siblings by centering on generic design evaluation with both description and screenshot input pathways.

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?

The description gives concrete usage direction: omit screenshots and pass a description to evaluate statelessly on the remote endpoint. It does not explicitly name alternatives but the two modes are clearly contrasted, and the limitation of the remote endpoint is stated, which effectively says when screenshots are not appropriate. No exclusions are mentioned, but the intent is clear.

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