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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds valuable nuance beyond annotations: deletion removes only the "public expressive state" while "structural tombstone evidence remains," signaling a soft-delete/accounting residue rather than full erasure.

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?

It is only two sentences and front-loads the action, but the second sentence's accounting language is cryptic and the first is jargon-heavy. Every sentence is short, yet clarity is sacrificed for atmosphere.

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 not be described. But with two required parameters at 0% schema coverage and no explanation of control_token, the definition leaves a critical invocation gap for a destructive operation.

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 0%, so neither identity_id nor control_token is explained structurally. The description does not clarify what control_token is or why it is required, though "controlled Garden identity" faintly implies an authorization concept.

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 names a delete operation against a "controlled Garden identity," which distinguishes it operationally from the identity_get/update/create siblings. However, "public expressive state" is opaque jargon and does not plainly state that the identity is being deleted, so an agent must infer the core effect.

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?

There is no guidance on when to use this deletion versus identity_update or other siblings, nor any stated prerequisites or warnings beyond the destructive annotation. The agent gets no explicit when-to-use or when-not-to-use context.

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