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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only, it never touches the repo.' It goes beyond annotations by disclosing the heuristic nature ('A heuristic text scan, not a structural guarantee'), which is crucial for managing expectations about false positives/negatives. This is valuable additional context that annotations cannot convey.

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?

Two sentences with no waste. The main purpose and specific problem list are front-loaded, followed by read-only and heuristic caveats. Every word earns its place; the structure is ideal for an agent to quickly grasp what the tool does and its limitations.

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 simple single-parameter tool with annotations covering safety and idempotency, the description covers the purpose, the list of problems, and the read-only/heuristic nature. The only minor gap is that it does not specify the return format (e.g., a list of problems with locations), but since there is no output schema, an agent might wonder about the exact shape of the result. This is a small omission given the tool's narrow scope.

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?

The schema has 100% coverage: the single parameter 'code' is described as 'the TSX snippet to check.' The tool description adds context that the code should use 'these components' and what it checks for, but it does not add syntax, format, or edge-case details about the parameter beyond what the schema already provides. With full schema coverage, the description does not need to compensate, so a baseline of 3 is appropriate.

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 clear verb ('Takes TSX... returns the glass-safety problems'), identifies the specific resource (TSX using these components), and enumerates the exact problems it detects (animated opacity, flex:1 collapse, clipped lens, conditional mount). It distinguishes itself from sibling tools by focusing on this narrow bug-checking task rather than component management or emission.

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 implies usage context—it is a heuristic text scan, not a structural guarantee—but it does not explicitly state when to use this tool over alternatives like verify_app or get_rules, nor does it mention any exclusions or prerequisites (e.g., 'use this for a quick check; for a definitive analysis, use verify_app'). The guidance is implicit, not explicit.

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