WhenLabs/When

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It details side effects (reads manifest files, writes/overwrites specific AI context files), explicitly states what it does not do ('Never modifies source code'), and describes the return behavior (plain-text summary, exit codes). It could improve by mentioning potential performance impact or file permission requirements, but covers core behavioral traits well.

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 efficiently structured with clear sections: purpose statement, usage guidelines, side effects, and return behavior. Every sentence adds essential information with zero waste. It's appropriately sized for a tool with multiple behaviors and parameters, and front-loads the core purpose.

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 tool with 2 parameters, no annotations, and no output schema, the description provides comprehensive context about behavior, side effects, and returns. It covers what the tool does, when to use it, what files it interacts with, and the output format. It could slightly improve by explicitly mentioning error handling details or dependencies, but is largely complete for the given complexity.

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 input schema has 100% description coverage, so the baseline is 3. The description adds value by explaining the practical implications of the 'dryRun' parameter ('report the files that would be written without touching disk') and suggesting usage ('Use this to preview changes before committing'), which goes beyond the schema's technical definition. It doesn't elaborate on 'path' parameter semantics, but the schema coverage is already complete.

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 purpose with specific verbs ('detect', 'regenerate') and resources ('tech stack', 'AI context files'), and distinguishes it from siblings by focusing on configuration file generation rather than validation, scanning, or task management. It explicitly names the files involved (CLAUDE.md, .cursorrules, etc.) and the configuration source (.aware.json).

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 provides explicit guidance on when to use ('after adding or removing a framework/language', 'when AI context files fall out of date', 'when onboarding a new agent') and when not to use ('Do not call on every turn — run once per session or after stack changes'). It clearly differentiates this from sibling tools by its specific use case of maintaining AI context files based on tech stack detection.

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