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

Annotations only declare destructiveHint=true; the description adds the consequences that matter: cascading deletion of every touching connection, irreversibility ('no undo'), the requirement to confirm with the user first, and the non-obvious side effect that purging a file or image also removes the stored file from Files.

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?

Front-loads the destructive action and its cascade before any routing advice. Four sentences, each carrying distinct load (what it does, irreversibility + confirmation, preferred alternative, file side effect, connection-only alternative) with no filler.

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 one-parameter destructive mutation with no output schema, this covers everything an agent needs: blast radius, irreversibility, user-confirmation prerequisite, hidden file deletion, and both alternative tools. Nothing material is left to inference.

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?

Single parameter with 100% schema coverage already documenting it as 'the object to destroy (exact object_id)', so the schema carries the load. The description reinforces the singular scope ('one object') and the exact-id requirement, but adds no further format or sourcing guidance beyond that.

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?

States a specific verb+resource ('Permanently delete one object from the user's graph') and immediately scopes the blast radius ('along with every connection touching it'). An agent can distinguish it from delete_graph_object, delete_graph_objects, and disconnect_graph_objects purely from this text.

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 names the preferred alternative (delete_graph_object, reversible, card confirmation) and the precise condition that selects this one ('only when they have said they want the data gone'). Also routes the narrower case to disconnect_graph_objects when the objects should survive.

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