start_scan

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

Adds substantial behavior beyond the readOnlyHint annotation: the call returns immediately, the work runs in the background, a full scan takes 1-5 minutes, and the time is dominated by 'large_files' and 'dot_cache'. It does not say what happens to a previously completed scan's results or whether concurrent scan starts are rejected.

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?

Three short sentences, each carrying distinct information: async contract, follow-up tool, duration profile, and the performance lever. The async/follow-up contract is front-loaded, which is exactly what an agent needs first.

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?

With no output schema, the description correctly redirects to get_scan_status for results, and the timing estimate sets realistic agent expectations. Minor gaps remain around concurrent invocation and result persistence, but nothing blocking for correct invocation.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds a genuinely new semantic: subsetting categories is 'much faster', which changes how an agent should choose the parameter. The omit-to-scan-everything behavior repeats the schema description.

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?

States a specific verb and effect ('Start scanning in the background') and immediately distinguishes the asynchronous behavior from the blocking sibling by naming get_scan_status. What exactly is scanned is only implied, but the categories enum and the cleanup-oriented siblings make the domain obvious.

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?

Gives clear follow-up routing ('follow up with get_scan_status') and a performance-driven usage rule ('Pass categories to scan only some of them (much faster)'). No exclusions are stated, e.g. what to do if a scan is already running or when cancel_scan is the right move.

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