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

Goes well beyond the destructiveHint=true annotation: it discloses that the delete is soft and reversible, that objects disappear from lists/search/chat, that restore_graph_objects with the returned deleted_ids undoes it, and that only owned objects are removed (never the root user node) with the rest returned as skipped. That is exactly the consequence/undo/partial-failure detail an agent needs before a destructive call.

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, each carrying distinct load — scope, permission condition, reversibility/undo path, sibling disambiguation, and ownership limits. The purpose and the guardrail are front-loaded, with no filler or repetition.

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 single-parameter tool with no output schema, the description covers what matters: the cap, the safety constraint, the undo path referencing the returned deleted_ids, partial-failure behavior (skipped), and even the chat-environment restriction. Nothing an agent needs in order to call it correctly is missing.

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?

There is one parameter at 100% schema coverage, and the schema already documents object_ids with the 200 cap, so the description largely restates it. The only marginal addition is that the ids must belong to the user's graph, which the description implies rather than specifies. Baseline 3 fits since the schema does the work.

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 a given list of objects from the user's graph') plus the scope limit of 200 ids per call. It explicitly positions itself against both siblings — 'One object is delete_graph_object; every object of a type is delete_graph_objects' — so an agent can pick the right tool without opening a 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 an explicit positive condition (user explicitly asked for these particular objects to go) and an explicit exclusion ('never to tidy up on your own initiative'), plus the alternative tools for the single-object and whole-type cases. It even discloses an environment restriction ('Not available in the YouSpot chat'), which is routing information an agent could not infer elsewhere.

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