rca_graph_delete

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

The description goes well beyond the destructiveHint annotation by stating the action is IRREVERSIBLE, that versioning/restore cannot rescue the record, that confirm=false aborts without deleting, and that a not_found error is returned for missing or other-user graphs. This is useful behavioral context the annotations alone cannot convey.

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 critical irreversibility warning is front-loaded, usage guidance follows, and the Args/Returns sections are clearly structured. The repetition of permanence is intentional emphasis rather than fluff.

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?

For a destructive tool, the description covers prerequisites, alternatives, error behavior, return value, and ownership caveats. There is no missing information an agent would need to select and invoke it correctly.

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 adds meaningful behavior to graph_id and especially confirm, including the abort-if-false outcome. It omits token and client_id, but the nested GraphDeleteInput schema already describes those unambiguously, so the gap is minor.

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 opens with a specific verb and resource: 'Delete a causal graph permanently.' It immediately distinguishes the tool from graph-editing siblings and from version restore, so an agent can tell exactly what this tool is for.

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?

It explicitly states when deletion is needed ('only need this to remove a graph entirely') and when it is not, naming rca_graph_add_node/remove_node/add_edge/remove_edge as alternatives for fixing a graph. It also gives the mandatory confirm precondition.

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