gk_code

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

The description adds valuable context: best-effort caveat for specified actions, and unknown action returns allowed list. But no annotations exist, and the description doesn't disclose potential side effects or authorization 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?

Two sentences, front-loaded with purpose, and no redundant text. The 'saves schema tokens' note is an interesting implementation detail but not directly actionable.

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 tool dynamic action design with a discovery mechanism partially compensates for the missing action list. However, the description lacks examples or explicit prerequisites, leaving the agent to discover actions at runtime.

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 description explains the invocation pattern (action + optional args) but doesn't enumerate the 21 actions or describe the expected structure of args for each action. Since schema coverage is 0%, this is a significant gap.

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 the tool provides code intel helpers for map/search/read, which differentiates it from other gk_* tools. The mention of specific action categories (council/swarm/pipeline/self_heal) adds specificity, but it doesn't explicitly contrast with sibling tools like gk_scan or gk_guard.

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 implies usage by instructing to pass action and args, and notes that certain actions are best-effort. However, it doesn't provide explicit guidance on when to choose this tool over alternatives, nor does it exclude cases.

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