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

Annotations only declare readOnlyHint=false, which is the minimum. The description adds substantial behavior beyond that: the delete is soft and reversible, objects disappear from lists/search/chat, restore_graph_objects with the returned deleted_ids undoes it, only owned objects are deleted, root user node is never deleted, and other objects come back as skipped. It also discloses the per-call ceiling (200) and the return shape (deleted_ids) even without an output schema. No contradiction with the annotation.

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?

Four sentences, no padding, each carrying distinct information: scope/limit, usage constraint, reversibility and undo path, sibling routing, ownership/root-node behavior, and environment exclusion. Front-loaded with the operation, then constraints. Every clause earns its place.

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 multi-object mutation with no output schema, the description covers safety (soft delete, owned-only, root-node protection), reversibility (restore_graph_objects + deleted_ids), routing among the three granularity siblings, the per-call limit, and environment availability. An agent has everything it needs to call this correctly and safely.

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 fully documented in the schema. The description adds the 200 object_ids ceiling, which is a mild reinforcement of the schema's own note, but no syntax, ownership, or format details beyond it. Baseline 3 is appropriate when the schema carries the burden.

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 states a specific verb+resource+scope: 'Delete a given list of objects from the user's graph, up to 200 object_ids in one call.' It explicitly distinguishes itself from siblings by naming delete_graph_object (single), delete_graph_objects (all of a type), and restore_graph_objects (the undo). An agent can route correctly without inspecting 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?

Provides explicit when-to-use ('only when the user explicitly asked for these particular objects to go'), when-not-to-use ('never to tidy up on your own initiative'), alternatives for other granularities (delete_graph_object for one; delete_graph_objects for every object of a type), and an environment exclusion ('Not available in the YouSpot chat'). This is about as complete as usage guidance gets.

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