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

Annotations already mark destructiveHint=true, so the safety profile is covered. The description adds useful behavioral context beyond annotations: the record is retained internally for a short window, the agent stops running, and confirmation is mandatory. This helps the agent understand recoverability and side effects.

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 short and front-loaded: it opens with the core action, immediately states the behavioral consequences, and places the critical confirmation requirement before the return note. No filler or redundant restatement.

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, the description is complete: it covers the effect, the retention behavior, the user-confirmation requirement, and the return type. There is no output schema, but the return description ('Dict with success status') suffices for this simple 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?

The input schema has 100% coverage with a single parameter, agent_id, already described as 'ID of the agent to delete.' The prose adds no further semantic detail, so the schema carries the burden; baseline 3 is appropriate.

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 an agent') and explains the observable consequences: the user stops seeing it and it stops running. This clearly distinguishes it from sibling tools like create_agent, update_agent, and get_agent_details.

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?

Includes an explicit operational guardrail: 'ALWAYS confirm with the user before calling this,' which tells the agent when not to invoke it casually. It does not name alternatives or exclusion cases, such as using update_agent instead for non-destructive changes, so it misses a top score.

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