Scan tests for cleanup

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

Annotations already declare readOnlyHint=true, and the description reinforces that by stating 'Read-only' and 'Never deletes'. Beyond the annotations, it adds behavioral context: what types of files it finds and that it returns a suggested removal set, providing a clear behavioral profile.

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 two sentences without redundancy. The first sentence packs key functionality with specific examples; the second adds return type and relationship to sibling tool. Every part earns its place.

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 the tool's purpose, return type (suggested removal set), and relationship to the sibling. It lacks mention of prerequisites (e.g., project must exist) or potential error states, but these are minor given the tool's simplicity and the presence of a single required parameter.

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 one parameter 'project' with no description (0% coverage). The description clarifies that the parameter identifies the project whose test directory is scanned, adding essential meaning beyond the raw schema.

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 it is a read-only deep-clean of the project's test/ directory, enumerating specific file types it finds (duplicate, stale, empty stub). It distinguishes itself from the sibling scan_board_cleanup by explicitly stating it never deletes and is a companion tool.

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 indicates it is a companion to scan_board_cleanup, implying a workflow where this scan identifies files for cleanup and the other tool likely performs deletion. However, it does not provide explicit when-not-to-use criteria or list alternative tools for similar tasks.

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