list_categories

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

readOnlyHint=true already covers the safety profile, and the description adds genuinely new behavior: categories carry a 'safe' vs 'review' risk level with an operational instruction to confirm 'review' items with the user. That's decision-relevant context beyond the annotation, though the shape of the returned list is left unspecified.

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?

Two short sentences, front-loaded with what the tool returns and immediately followed by the risk-level semantics that govern downstream actions. No filler or restatement of the tool name.

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 parameters and no output schema, the description must carry the return-value burden; it explains the risk-level field and the action it implies, which is the key information. It omits other likely fields (category names, item counts) and any mention of how this feeds start_scan, but nothing essential to calling it correctly is missing.

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 tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate on the input side.

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?

"What MacSweep can scan" plus the risk-level explanation makes clear this returns the set of scannable categories and their safety classification. It's a specific resource, but it never explicitly contrasts with list_items or start_scan, so an agent must infer the boundary from the name.

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?

Usage is only implied: the risk-level guidance ("check each item with the user") hints the agent should consult this before acting, but there is no explicit when-to-call, no prerequisites, and no reference to any of the eleven sibling tools such as list_items or start_scan.

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