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

Goes well beyond destructiveHint=true: it discloses that the delete is soft (hidden from lists, search, and chat but retained and restorable), that only owned objects qualify, that the root user node is protected, and — crucially — that in chat it does not delete at all but returns instructions for a confirmation card. These are non-obvious behaviors an agent could not infer from annotations or schema.

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?

Five short sentences, front-loaded with the action, then the permission gate, then the destructive-behavior caveat. Every sentence carries information the agent needs; nothing is repeated from the schema or annotations.

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 single-parameter mutation with no output schema, the description covers safety profile, identity resolution, ownership limits, and the unusual chat confirmation round-trip. There is no material gap left for an agent deciding whether and how to call it.

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% and the single parameter is documented in the schema, so the baseline is 3. The description adds real meaning on top: where to get the object_id (search_graph_objects) and the ownership constraint on which ids are valid.

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 and resource ('Delete an object from the user's graph') and immediately qualifies it as a soft delete with retained data and restore capability, which distinguishes it in spirit from purge_graph_object. It does not explicitly name the bulk siblings (delete_graph_objects, delete_selected_graph_objects) or purge_graph_object, so an agent must infer the singular-vs-bulk split from the name alone.

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?

Gives an explicit trigger ('only when the user explicitly asks to delete or remove a specific object') and an explicit exclusion ('never to tidy up on your own initiative'), which is exactly the guardrail an agent needs. It also points to search_graph_objects as the way to obtain the id. It stops short of naming alternative tools for bulk deletion or permanent purge, so the routing across the delete family is incomplete.

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