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 this with 'Read-only' and 'Never deletes'. It also discloses what types of files are detected (duplicates, stale, empty stubs) and that it returns a suggested removal set. No contradictions 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 concise at two sentences, with no wasted words. It front-loads the main action and purpose, immediately followed by specifics and a critical caveat ('Never deletes').

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 the single required parameter, clear annotations, and no output schema, the description adequately covers the tool's scope: what it inspects, what it finds, and what it returns (a suggested removal set). It could optionally mention return format, but the description is functionally complete.

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?

There is only one parameter 'project' with no schema description coverage. The description mentions 'project's test/ dir' but does explain the format, constraints, or example values of the project string. Since schema coverage is 0%, the description should compensate but does so only minimally.

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 precisely states the tool's function: 'Read-only deep-clean of the project's test/ dir' and enumerates three specific detection categories (byte-identical duplicates, stale files with missing ticket IDs, empty stub files). It also explicitly distinguishes itself from the sibling tool 'scan_board_cleanup', making the purpose unmistakable.

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 clearly indicates that the tool is read-only and a companion to 'scan_board_cleanup', implying when to use it (for detection, not deletion). However, it does not explicitly state when not to use it or list alternative tools beyond the named companion.

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