gk_guard

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

With no annotations, description discloses key behavioral traits: one-turn arming, clearing, file-scope limitation, host-hook dependency, and fallback for unknown actions. This goes well beyond minimal requirements.

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 compact and front-loaded with the purpose. Each sentence adds unique information, though phrases like 'ship default max 1 path' and 'saves schema tokens' are cryptic and could confuse.

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?

Covers purpose, actions, conditions, and invocation pattern; output schema exists so return values aren't required. Minor gaps around args formatting keep it from a 5.

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?

Description names all three actions (set_paths, end_turn, Ultradeep) and explains that action is required with optional args={}, compensating for the schema's 0% description coverage. It doesn't specify args structure for each action but provides enough orientation.

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 first sentence 'Write allowlist for host PreToolUse' states a specific action and resource, and subsequent sentences detail the tool's scope. It clearly distinguishes from sibling tools by focusing on guarding/allowlisting rather than code, scan, route, etc.

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?

Provides clear context: set_paths arms one turn, end_turn clears, ultradeep syncs current file only, and blocks native Write only when host hook is wired. It doesn't explicitly name alternatives/exclusions, but the action-specific instructions make usage conditions clear.

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