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

Annotations only provide readOnlyHint=false, so the description usefully adds scope and constraint behavior: cap of 200 ids per call, only the user's own deleted objects are returned, merged records are excluded, and purged objects are unrecoverable. It stops short of describing partial-failure behavior (e.g. what happens when some ids are invalid or not restorable), which keeps it from a 5.

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 core action, then layers constraint, boundary, and failure cases in three tight follow-on clauses. Every sentence earns its place and there is no redundancy.

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 tool with no output schema, the description covers the action, the cap, the ownership constraint, and the key failure boundaries. The main remaining gap is the return shape and how partial successes/failures are reported, which the agent would need in practice.

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 description coverage is 100%, so the object_ids parameter is already documented with type and the 200 limit. The description restates the 200 cap and adds that only the caller's own deleted objects qualify as valid ids, but contributes no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 ('Bring back objects the user deleted') and immediately distinguishes itself from siblings by naming delete_graph_object and delete_selected_graph_objects as the operations it undoes. An agent can tell it apart from merge/unmerge/purge tools without opening any schema.

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 explicit when-to-use ('the undo for delete_graph_object and delete_selected_graph_objects'), explicit exclusions ('a record that was merged into another is not restored here') and names the correct alternative (unmerge_graph_objects). Also clarifies that purged objects cannot be restored, so the agent knows when this call will not help.

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