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

The description adds meaningful behavioral context beyond annotations: 'No files are written,' 'read-only Swift token output,' and 'uses no network.' This complements the readOnlyHint, idempotentHint, and destructiveHint annotations and provides concrete effects useful to an agent.

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 reasonably structured but contains redundancy: 'No files are written' is stated twice, and 'Use: use before...' repeats the prior 'Use this before...' sentence. It also includes inaccurate parameter names, adding noise. It could be tightened without losing important information.

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?

The description covers when to use the tool and side-effect transparency, and the schema covers all parameters plus an output schema. However, the inaccurate parameter references create a notable gap and could cause an agent to pass non-existent parameters. The overall context is adequate but not complete due to this mismatch.

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% description coverage for all actual parameters (format, source, namespace, sourcePath), so the baseline is 3. However, the description introduces 'tokens', 'enumName', and 'accessLevel' which are not in the schema, potentially misleading an agent. It also omits any reference to the real parameters' nuances, making the description add confusion rather than 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 clearly states the tool's function: 'Ingest design tokens from JSON, JS/TS object exports, or CSS variables and return a SwiftUI token enum.' This is a specific verb+resource+output combination that clearly distinguishes it from sibling tools like axint.compile, axint.run, and axint.validate.

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 explicitly says 'Use before generating Swarm-style views/components' and 'use before view/component generation when a design system should be preserved,' providing clear when-to-use context. It doesn't mention when not to use the tool or name alternatives, but the intended context is well-defined.

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