clear_graph

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

With no annotations, description carries full burden. It discloses destructive nature ('Clear ALL...'), rewindability via event-sourcing, and prerequisites for large graphs. However, does not explicitly state irreversibility without rewind or impact on branches.

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 sentences with no fluff. First sentence states primary action, second gives warning, third provides behavioral trait and alternative. Information is front-loaded and efficient.

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 core action, usage caveats, rewind capability. Lacks details on return value, effect on other branches, or whether the operation is atomic. But sufficient for a destructive tool with rewind option.

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% but description adds context: reason is required for >10 entities, confirm_token format is 'CLEAR_<count>', and ties parameters to usage condition. Adds value beyond schema.

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 'Clear ALL entities and relations from the graph' with specific verb and resource. It distinguishes from sibling tools like delete_entities and delete_relations by emphasizing the global scope.

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?

Explicitly warns 'Use sparingly!' and specifies condition for large graphs requiring reason and confirm_token. Also provides alternative using get_state_at(timestamp) for rewind, guiding when to use this tool versus recovery.

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