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

Annotations already declare destructiveHint=true and non-idempotence, but the description goes further: it enumerates exactly what is destroyed (properties, relationship/action occurrences, mentions, ownership rows), states there is no undo or tombstone, notes it refuses graph plumbing and the _system.* namespace, and discloses the write-access requirement and audit-log behavior of `reason`.

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-loaded with the destructive action and the IRREVERSIBLE warning, then proceeds through consequences, usage, exclusions, and parameter notes. Dense rather than padded, though the multi-paragraph layout is longer than strictly necessary for a three-parameter tool.

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?

An output schema exists, so return values need no explanation. The description covers preconditions, destructive side effects, refusals, and audit behavior — everything an agent needs to invoke this 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 0%, so the description must compensate. It explains `reason` (optional, written to the audit log) and hints at `object_id` via the get_object precondition, but says nothing about `memory`, leaving one of three parameters undocumented in both schema and prose.

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 ('delete'), resource ('one object'), and cascade scope ('everything hanging off it'), plus the irreversibility. It explicitly contrasts itself with merge_objects, so an agent can distinguish it from siblings without opening schemas.

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 when-to-use ('a wrong fact, a test row, something a person asked to have removed') and when-not-to-use (duplicates → merge_objects, with the reason merge is better). It also prescribes prerequisites: confirm with the user, run get_object first, prefer get_change_impact when dependents may exist.

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