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

The description significantly adds to the annotations by explaining that system agents are rejected with a clear message, idempotent deletion of unknown IDs returns NOT_FOUND, and the tier restriction (sp500+). It also tells users how to identify system agents via is_system on get_agent/list_agents. This is rich behavioral context beyond the destructive/idempotent hints.

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 compact and front-loaded: first sentence states the core action, the second adds exceptions, and the third covers idempotency and tiering. Every sentence carries unique information without redundancy.

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 simple delete operation with one parameter and an output schema, the description covers purpose, ownership, system-agent exclusions, idempotent behavior, and access tiering. It is fully self-contained and leaves no significant gaps for an agent to invoke the tool correctly.

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 schema already fully documents agent_id (identifier of the agent to delete), so the description adds no new parameter-specific syntax. It does reinforce that the ID refers to a caller-owned standing agent, but this is more of a behavior note than parameter semantics. Baseline 3 applies due to 100% schema coverage.

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 uses a specific verb ('Delete') and resource ('standing agents by id'), clearly distinguishing it from sibling tools like delete_agent_memory and delete_alert. It also specifies ownership ('caller's own') and agent type, making the tool's scope unambiguous.

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?

The description provides clear context on when to use this tool (for deleting caller-owned agents) and when not to (system agents, listed as rejected). It references get_agent/list_agents for checking is_system and mentions the tier restriction. However, it does not explicitly name alternatives for other deletion scenarios, though the context is strong.

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