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

The description discloses that deletion is permanent, that the scale can be millions of records, and crucially that the tool does not delete in chat but returns instructions for a confirmation card that the user must click. These behaviors go well beyond the sparse annotations and help the agent set correct expectations.

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?

The description is information-dense but every sentence earns its place: purpose, alternative, permanence/scale, explicit-consent rule, cardinality, and chat confirmation behavior. The key distinction is front-loaded and the sentence order supports fast decision-making.

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 dangerous bulk-delete tool with one parameter and no output schema, the description covers what is deleted, when it is appropriate, its permanence, how the confirmation flow works in chat, and the constraints on the parameter. There is no significant missing context that would cause an agent to misuse 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?

With 100% schema coverage, the schema already documents object_type well, but the description adds the important cardinality constraint of naming exactly one type per call and gives a concrete example. It also points to search_graph_objects and type counts as sources for valid types, adding useful context beyond the schema.

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 leads with a specific verb and resource: delete every object of one type from the user's graph. It explains the bulk category-clearing use case with an example and explicitly contrasts it with delete_graph_object for single-record deletion, distinguishing it from the most similar sibling.

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?

It states exactly when to use the tool (user asks for an entire category to go), when not to (single object → delete_graph_object), and adds constraints: only after explicit request, one type per call, and that in chat it only schedules deletion via a confirmation card. This is explicit guidance an agent can act on directly.

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