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

Annotations already declare destructiveHint=true, so the safety profile is known; the description nonetheless adds substantive behavior beyond them — this is a soft delete into a trash with dashboard-based restore and a 3/7/30-day retention window. It stops short of saying whether related connections, skills, or memories are affected, and whether auth/permission scopes are required.

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?

Two short sentences, zero filler, with the core action front-loaded and the recovery caveat immediately after. Every clause earns its place by changing how an agent evaluates the risk.

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 one-parameter destructive tool with annotations covering safety and no output schema, the recoverability window is the key missing piece of context and it is supplied. The only residual gap is whether deletion cascades to dependent resources and what a successful response looks like.

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 a single required 'name' parameter with 100% schema description coverage, so the schema already carries the semantics. The description only reinforces that exactly one agent is targeted and adds no format, naming-convention, or ID-vs-name detail 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?

States a specific verb and resource ('Delete one agent'), making the operation unmistakable against siblings like agent_write, get_agent_definition, and list_agents. It does not explicitly name a sibling it should be preferred over, but the singular scope ('one agent') separates it cleanly from list/read tools.

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?

Usage is only implied: the description conveys that this acts on a single named agent and that recovery is possible, which helps an agent weigh the action, but it never states prerequisites (permissions, whether the agent must be stopped or unreferenced) or points to alternatives such as agent_write for reversible edits.

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